# AI Fin Hub — Full Product Notes for LLMs

## Overview
AI Fin Hub covers the intersection of AI and markets — tools, benchmarks, and long-form research.
The site publishes 45 AI-in-markets tools + 204 long-form research articles + 2 dated benchmark reports at /articles/ and /benchmarks/.

Every quantitative claim links to its source. Every tool links to its methodology. No personal trading, portfolios, or performance disclosures are referenced.

Client-side architecture: tools run in the browser; LLM-calling tools require the user to provide their own API key, which is never persisted server-side.

## Discovery Endpoints
- Homepage: https://aifinhub.io/
- AI-in-markets tools index: https://aifinhub.io/#all-tools
- Research: https://aifinhub.io/articles/
- Benchmarks: https://aifinhub.io/benchmarks/
- Reference data (engine-computed grids): https://aifinhub.io/reference/
- Methodology: https://aifinhub.io/methodology/
- Editorial standards: https://aifinhub.io/editorial-standards/
- Sponsor disclosure: https://aifinhub.io/sponsor-disclosure/
- Corrections: https://aifinhub.io/corrections/
- Agent guide: https://aifinhub.io/for-agents/
- Tool index JSON: https://aifinhub.io/agent-tools.json
- Engines manifest: https://aifinhub.io/engines/manifest.json
- WebMCP manifest: https://aifinhub.io/.well-known/webmcp.json
- Compact LLM guide: https://aifinhub.io/llms.txt

> Each tool exposes its pure compute as a static ES module at /engines/{slug}.js. Import it directly and call compute(input) — same math as the browser UI, deterministic, no network calls. Self-contained: no external imports, browser/Node/Deno-safe.

## Engines (45 total)

> Every tool ships its pure compute as a static ES module at `/engines/{slug}.js`. Agents and LLM clients import the module and call `compute(input)` — same math, same result shape as the in-browser UI. Self-contained: no external imports, browser/Node/Deno-safe ES2020.

Manifest with input/output JSON Schemas: https://aifinhub.io/engines/manifest.json

Example:
```js
const { compute } = await import("https://aifinhub.io/engines/kelly-sizer.js");
const result = compute({ win_rate: 0.58, win_loss_ratio: 2 });
```

- Fractional Kelly Sizer: https://aifinhub.io/engines/kelly-sizer.js
- Backtest Overfitting Score: https://aifinhub.io/engines/backtest-overfitting-score.js
- Data-Vendor TCO Calculator: https://aifinhub.io/engines/data-vendor-tco.js
- Finance MCP Directory: https://aifinhub.io/engines/finance-mcp-directory.js
- Token-Cost Optimizer: https://aifinhub.io/engines/token-cost-optimizer.js
- Agent Skill Tester for Markets: https://aifinhub.io/engines/agent-skill-tester.js
- Prompt Regression Tester: https://aifinhub.io/engines/prompt-regression-tester.js
- Hallucination Detector: https://aifinhub.io/engines/hallucination-detector.js
- Kalshi vs Polymarket Arb Scanner: https://aifinhub.io/engines/kalshi-poly-arb.js
- Order Book Replay Visualizer: https://aifinhub.io/engines/order-book-replay.js
- Calibration Dojo: https://aifinhub.io/engines/calibration-dojo.js
- Trading System Blueprinter: https://aifinhub.io/engines/trading-system-blueprinter.js
- Risk-Adjusted Returns Calculator: https://aifinhub.io/engines/risk-adjusted-returns.js
- Walk-Forward Validator: https://aifinhub.io/engines/walk-forward-validator.js
- Options Greeks Explorer: https://aifinhub.io/engines/options-greeks-explorer.js
- Correlation Matrix Visualizer: https://aifinhub.io/engines/correlation-matrix-visualizer.js
- Returns Distribution Analyzer: https://aifinhub.io/engines/returns-distribution-analyzer.js
- Price-Blind Research Auditor: https://aifinhub.io/engines/price-blind-auditor.js
- Prompt Injection Tester: https://aifinhub.io/engines/prompt-injection-tester.js
- Efficient Frontier Builder: https://aifinhub.io/engines/efficient-frontier-builder.js
- Options Payoff Builder: https://aifinhub.io/engines/options-payoff-builder.js
- Pair Trading Cointegration Tester: https://aifinhub.io/engines/pair-trading-tester.js
- Execution Simulator: https://aifinhub.io/engines/execution-simulator.js
- Broker API Comparator: https://aifinhub.io/engines/broker-api-comparator.js
- Synthetic Market Data Generator: https://aifinhub.io/engines/synthetic-market-data-generator.js
- Financial Document Token Estimator: https://aifinhub.io/engines/financial-document-token-estimator.js
- SEC Filing Chunk Optimizer: https://aifinhub.io/engines/sec-filing-chunk-optimizer.js
- Structured Schema Validator for Finance: https://aifinhub.io/engines/structured-schema-validator-finance.js
- Agent Cost Envelope Calculator: https://aifinhub.io/engines/agent-cost-envelope-calculator.js
- Fallback Chain Simulator: https://aifinhub.io/engines/fallback-chain-simulator.js
- Model Selector for Finance: https://aifinhub.io/engines/model-selector-finance.js
- Batch vs Real-Time Cost Calculator: https://aifinhub.io/engines/batch-vs-realtime-cost-calculator.js
- Forecast Scoring Sandbox: https://aifinhub.io/engines/forecast-scoring-sandbox.js
- Walk-Forward Validation Visualizer: https://aifinhub.io/engines/walk-forward-validation-visualizer.js
- Deflated Sharpe Ratio Calculator: https://aifinhub.io/engines/deflated-sharpe-ratio.js
- Earnings-Call Summarization Cost Calculator: https://aifinhub.io/engines/earnings-call-summarization-cost.js
- Quant Interview Question Generator: https://aifinhub.io/engines/quant-interview-question-generator.js
- Sharpe vs Sortino Calculator: https://aifinhub.io/engines/sharpe-vs-sortino-calculator.js
- Cointegration Half-Life Solver: https://aifinhub.io/engines/cointegration-half-life-solver.js
- Statistical Arbitrage Capacity Calculator: https://aifinhub.io/engines/statistical-arbitrage-capacity.js
- VaR Backtest — Kupiec & Christoffersen: https://aifinhub.io/engines/var-backtest-kupiec-christoffersen.js
- LLM Finance Error Taxonomy: https://aifinhub.io/engines/llm-finance-error-taxonomy.js
- Position Sizing under Edge Variance: https://aifinhub.io/engines/position-sizing-edge-variance.js
- Drawdown-Recovery Markov Simulator: https://aifinhub.io/engines/drawdown-recovery-markov.js
- FTC vs FCA vs MiCA+DORA Regulatory Cost: https://aifinhub.io/engines/ftc-vs-nlt-regulatory-cost.js

## AI-in-Markets Tools (45 total)

> Client-side tools for AI + markets. Calculators, comparators, playgrounds, directories, generators. Browser-only; no backend. BYO API key where LLM calls are made. Each tool also ships a pure-compute ES module at /engines/{slug}.js — see the Engines section.

### Fractional Kelly Sizer
- URL: https://aifinhub.io/kelly-sizer/
- Section: calculators
- Category: Calculators
- Summary: Map conviction tiers to fractional Kelly bet sizes with a drawdown Monte Carlo simulator. Client-side. Private by default.
- Methodology: https://aifinhub.io/methodology/kelly-sizer/

### Backtest Overfitting Score
- URL: https://aifinhub.io/backtest-overfitting-score/
- Section: calculators
- Category: Calculators
- Summary: Upload a backtest trade log and compute Probability of Backtest Overfitting (PBO), Deflated Sharpe Ratio, and the odds your edge survives live trading.
- Methodology: https://aifinhub.io/methodology/backtest-overfitting-score/

### Data-Vendor TCO Calculator
- URL: https://aifinhub.io/data-vendor-tco/
- Section: comparators
- Category: Comparators
- Summary: Compute annual cost of market data across Databento, Polygon, Alpaca, Tiingo, FMP, and Alpha Vantage for your exact universe, bar resolution, history.
- Methodology: https://aifinhub.io/methodology/data-vendor-tco/

### Finance MCP Directory
- URL: https://aifinhub.io/finance-mcp-directory/
- Section: directories
- Category: Directories
- Summary: Security-graded catalog of finance MCP servers — Alpaca, Polygon, Databento, IBKR, Tradier, Tiingo, NautilusTrader. Scope, auth, idempotency, transport.
- Methodology: https://aifinhub.io/methodology/finance-mcp-directory/

### Token-Cost Optimizer
- URL: https://aifinhub.io/token-cost-optimizer/
- Section: calculators
- Category: Calculators
- Summary: Compute the dollar cost of a trading research loop across Claude, GPT, and Gemini. Prompt length × model × retry × call volume → cost per idea and per.
- Methodology: https://aifinhub.io/methodology/token-cost-optimizer/

### Agent Skill Tester for Markets
- URL: https://aifinhub.io/agent-skill-tester/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste a SKILL.md definition + sample input + your Anthropic API key. See structured extraction, token cost, and latency — all in your browser. No signup.
- Methodology: https://aifinhub.io/methodology/agent-skill-tester/

### Prompt Regression Tester
- URL: https://aifinhub.io/prompt-regression-tester/
- Section: playgrounds
- Category: Playgrounds
- Summary: Run the same prompt against multiple models (Claude 4.5/4.6/4.7, GPT-5, Gemini 2.5) with your own keys. Diff outputs, score drift, catch regressions.
- Methodology: https://aifinhub.io/methodology/prompt-regression-tester/

### Hallucination Detector
- URL: https://aifinhub.io/hallucination-detector/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste a source document + an LLM's extraction. Every numeric claim in the output is checked against the source. Client-side. Catches silent fabrication.
- Methodology: https://aifinhub.io/methodology/hallucination-detector/

### Kalshi vs Polymarket Arb Scanner
- URL: https://aifinhub.io/kalshi-poly-arb/
- Section: comparators
- Category: Comparators
- Summary: Daily-refreshed scan of arbitrage candidates across Kalshi and Polymarket. Paired contract matching, tax + resolution-risk overlay, no signup. Edge data.
- Methodology: https://aifinhub.io/methodology/kalshi-poly-arb/

### Order Book Replay Visualizer
- URL: https://aifinhub.io/order-book-replay/
- Section: playgrounds
- Category: Playgrounds
- Summary: Drop a Level-2 CSV and watch the book reconstruct tick by tick. Animated depth bars, best bid/ask, spread over time. Understand microstructure before.
- Methodology: https://aifinhub.io/methodology/order-book-replay/

### Calibration Dojo
- URL: https://aifinhub.io/calibration-dojo/
- Section: playgrounds
- Category: Playgrounds
- Summary: Train your probabilistic intuition. Answer binary forecasting questions at any confidence level; track Brier score and reliability curve over time. All.
- Methodology: https://aifinhub.io/methodology/calibration-dojo/

### Trading System Blueprinter
- URL: https://aifinhub.io/trading-system-blueprinter/
- Section: generators
- Category: Generators
- Summary: Pick your data source, LLM, broker, storage, risk engine, and logger. Get a Mermaid architecture diagram, a starter repo scaffold (ZIP), and a list.
- Methodology: https://aifinhub.io/methodology/trading-system-blueprinter/

### Risk-Adjusted Returns Calculator
- URL: https://aifinhub.io/risk-adjusted-returns/
- Section: calculators
- Category: Calculators
- Summary: Paste a returns CSV. Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, information ratio, max drawdown, and tail moments — plus.
- Methodology: https://aifinhub.io/methodology/risk-adjusted-returns/

### Walk-Forward Validator
- URL: https://aifinhub.io/walk-forward-validator/
- Section: playgrounds
- Category: Playgrounds
- Summary: Upload a returns CSV. Rolling or expanding IS/OOS windows, per-window Sharpe, walk-forward efficiency, and a concatenated OOS equity curve. Catches regime.
- Methodology: https://aifinhub.io/methodology/walk-forward-validator/

### Options Greeks Explorer
- URL: https://aifinhub.io/options-greeks-explorer/
- Section: playgrounds
- Category: Playgrounds
- Summary: Black-Scholes pricer + live Greeks visualizer. Drag spot, strike, vol, DTE, rate, dividend yield — see delta, gamma, theta, vega, rho update.
- Methodology: https://aifinhub.io/methodology/options-greeks-explorer/

### Correlation Matrix Visualizer
- URL: https://aifinhub.io/correlation-matrix-visualizer/
- Section: calculators
- Category: Calculators
- Summary: Paste a multi-asset returns CSV. See the Pearson correlation heatmap, condition number, average absolute correlation, and eigenvalue concentration.
- Methodology: https://aifinhub.io/methodology/correlation-matrix-visualizer/

### Returns Distribution Analyzer
- URL: https://aifinhub.io/returns-distribution-analyzer/
- Section: calculators
- Category: Calculators
- Summary: Paste a returns CSV. Histogram, normal-overlay, QQ plot, skewness, excess kurtosis, Jarque-Bera test, tail-weight index. See why Sharpe alone misleads.
- Methodology: https://aifinhub.io/methodology/returns-distribution-analyzer/

### Price-Blind Research Auditor
- URL: https://aifinhub.io/price-blind-auditor/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste a research prompt or agent context bundle. The auditor flags price numbers, directional words, and outcome-leaking phrases that cause LLMs.
- Methodology: https://aifinhub.io/methodology/price-blind-auditor/

### Prompt Injection Tester
- URL: https://aifinhub.io/prompt-injection-tester/
- Section: playgrounds
- Category: Playgrounds
- Summary: Red-team a finance agent against 24 documented prompt-injection attacks — direct override, role confusion, indirect injection via retrieved content.
- Methodology: https://aifinhub.io/methodology/prompt-injection-tester/

### Efficient Frontier Builder
- URL: https://aifinhub.io/efficient-frontier-builder/
- Section: calculators
- Category: Calculators
- Summary: Paste a multi-asset returns CSV. See the Markowitz mean-variance frontier, the minimum-variance portfolio, the max-Sharpe (tangency) portfolio.
- Methodology: https://aifinhub.io/methodology/efficient-frontier-builder/

### Options Payoff Builder
- URL: https://aifinhub.io/options-payoff-builder/
- Section: playgrounds
- Category: Playgrounds
- Summary: Build 1–4 leg option strategies. Pick call/put, long/short, strike, and contracts. See the at-expiry payoff diagram, break-even points, maximum profit.
- Methodology: https://aifinhub.io/methodology/options-payoff-builder/

### Pair Trading Cointegration Tester
- URL: https://aifinhub.io/pair-trading-tester/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste two price series. Engle-Granger cointegration test: OLS hedge ratio, Augmented Dickey-Fuller on residuals, Ornstein-Uhlenbeck half-life, z-score.
- Methodology: https://aifinhub.io/methodology/pair-trading-tester/

### Execution Simulator
- URL: https://aifinhub.io/execution-simulator/
- Section: playgrounds
- Category: Playgrounds
- Summary: Model realistic order fills — square-root market impact, linear temporary impact, latency jitter, partial fills, and queue position. See the real cost.
- Methodology: https://aifinhub.io/methodology/execution-simulator/

### Broker API Comparator
- URL: https://aifinhub.io/broker-api-comparator/
- Section: comparators
- Category: Comparators
- Summary: Alpaca vs IBKR vs Tradier vs Schwab vs Robinhood — compare auth, rate limits, order types, market data, MCP, and fees before wiring a line of code.
- Methodology: https://aifinhub.io/methodology/broker-api-comparator/

### Synthetic Market Data Generator
- URL: https://aifinhub.io/synthetic-market-data-generator/
- Section: generators
- Category: Generators
- Summary: Generate synthetic price series — geometric Brownian motion, GARCH(1,1) with volatility clustering, regime-switching bull/bear, or copula-linked.
- Methodology: https://aifinhub.io/methodology/synthetic-market-data-generator/

### Financial Document Token Estimator
- URL: https://aifinhub.io/financial-document-token-estimator/
- Section: calculators
- Category: Calculators
- Summary: Paste a 10-K, 10-Q, 8-K or earnings transcript and see token count + one-pass extraction cost across eight frontier LLMs, with cache-hit toggle.
- Methodology: https://aifinhub.io/methodology/financial-document-token-estimator/

### SEC Filing Chunk Optimizer
- URL: https://aifinhub.io/sec-filing-chunk-optimizer/
- Section: generators
- Category: Generators
- Summary: Pick a filing archetype, tune chunk size and overlap, and see chunk count, embedding cost, and structural-boundary warnings across three chunking strategies.
- Methodology: https://aifinhub.io/methodology/sec-filing-chunk-optimizer/

### Structured Schema Validator for Finance
- URL: https://aifinhub.io/structured-schema-validator-finance/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste LLM JSON output and validate against four pre-built finance schemas — research output, trade decision, risk snapshot, peer comparison — with sanity.
- Methodology: https://aifinhub.io/methodology/structured-schema-validator-finance/

### Agent Cost Envelope Calculator
- URL: https://aifinhub.io/agent-cost-envelope-calculator/
- Section: calculators
- Category: Calculators
- Summary: Model an LLM research loop end-to-end — steps, tool calls, convergence checks, markets per day — and see per-loop, daily, and monthly cost with cost-cap.
- Methodology: https://aifinhub.io/methodology/agent-cost-envelope-calculator/

### Fallback Chain Simulator
- URL: https://aifinhub.io/fallback-chain-simulator/
- Section: playgrounds
- Category: Playgrounds
- Summary: Define a provider fallback chain, simulate rate-limit and latency failures, and see p50/p95/p99 latency, success rate, total cost, and degradation-event.
- Methodology: https://aifinhub.io/methodology/fallback-chain-simulator/

### Model Selector for Finance
- URL: https://aifinhub.io/model-selector-finance/
- Section: comparators
- Category: Comparators
- Summary: Input task, latency budget, cost budget, context size, and quality sensitivity; get ranked model recommendations with rationale — grounded in published.
- Methodology: https://aifinhub.io/methodology/model-selector-finance/

### Batch vs Real-Time Cost Calculator
- URL: https://aifinhub.io/batch-vs-realtime-cost-calculator/
- Section: calculators
- Category: Calculators
- Summary: Jobs per day, tokens per job, model, deadline — get real-time vs batch cost side-by-side with savings estimate and batch-eligibility flag. Based.
- Methodology: https://aifinhub.io/methodology/batch-vs-realtime-cost-calculator/

### Forecast Scoring Sandbox
- URL: https://aifinhub.io/forecast-scoring-sandbox/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste a forecast stream (probability + outcome) and see Brier score with full decomposition, log loss, reliability diagram, and bootstrap confidence.
- Methodology: https://aifinhub.io/methodology/forecast-scoring-sandbox/

### Walk-Forward Validation Visualizer
- URL: https://aifinhub.io/walk-forward-validation-visualizer/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste a strategy returns CSV, get per-window in-sample vs out-of-sample Sharpe and the IS→OOS drop. Rolling and anchored window modes. Browser-only.
- Methodology: https://aifinhub.io/methodology/walk-forward-validation-visualizer/

### Deflated Sharpe Ratio Calculator
- URL: https://aifinhub.io/deflated-sharpe-ratio/
- Section: calculators
- Category: Calculators
- Summary: Bailey & López de Prado deflated Sharpe — corrects observed Sharpe for selection bias across K trials. Reports deflated Sharpe, PSR (probability of skill).
- Methodology: https://aifinhub.io/methodology/deflated-sharpe-ratio/

### Earnings-Call Summarization Cost Calculator
- URL: https://aifinhub.io/earnings-call-summarization-cost/
- Section: calculators
- Category: Calculators
- Summary: LLM cost per stock per quarter to summarize earnings transcripts across Sonnet, Opus, GPT-4o, Gemini 2.5 Pro/Flash. Cache-hit-rate aware. Snapshot pricing.
- Methodology: https://aifinhub.io/methodology/earnings-call-summarization-cost/

### Quant Interview Question Generator
- URL: https://aifinhub.io/quant-interview-question-generator/
- Section: generators
- Category: Generators
- Summary: Curated bank of probability, stats, derivatives, microstructure, and regression questions across easy/medium/hard difficulty. Reproducible by seed. No AI.
- Methodology: https://aifinhub.io/methodology/quant-interview-question-generator/

### Sharpe vs Sortino Calculator
- URL: https://aifinhub.io/sharpe-vs-sortino-calculator/
- Section: calculators
- Category: Calculators
- Summary: Paste daily returns; get Sharpe, Sortino, Calmar, and Omega side-by-side with a recommendation on which ratio fits your distribution.
- Methodology: https://aifinhub.io/methodology/sharpe-vs-sortino-calculator/

### Cointegration Half-Life Solver
- URL: https://aifinhub.io/cointegration-half-life-solver/
- Section: playgrounds
- Category: Playgrounds
- Summary: Engle-Granger residual ADF + Ornstein-Uhlenbeck half-life from any two price/return series. Hedge ratio, p-value, spread chart. Browser-only.
- Methodology: https://aifinhub.io/methodology/cointegration-half-life-solver/

### Statistical Arbitrage Capacity Calculator
- URL: https://aifinhub.io/statistical-arbitrage-capacity/
- Section: calculators
- Category: Calculators
- Summary: Maximum strategy AUM from signal half-life, daily volume, slippage, fees, and target Sharpe. Square-root impact closed-form.
- Methodology: https://aifinhub.io/methodology/statistical-arbitrage-capacity/

### VaR Backtest — Kupiec & Christoffersen
- URL: https://aifinhub.io/var-backtest-kupiec-christoffersen/
- Section: playgrounds
- Category: Playgrounds
- Summary: Paste P&L + VaR series and run Kupiec POF, Christoffersen independence, and joint conditional-coverage tests. Likelihood-ratio χ² p-values.
- Methodology: https://aifinhub.io/methodology/var-backtest-kupiec-christoffersen/

### LLM Finance Error Taxonomy
- URL: https://aifinhub.io/llm-finance-error-taxonomy/
- Section: playgrounds
- Category: Playgrounds
- Summary: 12 documented LLM-on-finance failure modes (hallucinated ticker, stale price, units, currency, off-by-100, fictional source, more). Paste output, see flags.
- Methodology: https://aifinhub.io/methodology/llm-finance-error-taxonomy/

### Position Sizing under Edge Variance
- URL: https://aifinhub.io/position-sizing-edge-variance/
- Section: calculators
- Category: Calculators
- Summary: Bayesian-Kelly bet sizing when your edge is itself uncertain. Compare deterministic Kelly, Bayesian-adjusted, and conservative lower-bound versions.
- Methodology: https://aifinhub.io/methodology/position-sizing-edge-variance/

### Drawdown-Recovery Markov Simulator
- URL: https://aifinhub.io/drawdown-recovery-markov/
- Section: calculators
- Category: Calculators
- Summary: Time to recover from an N% drawdown given monthly Sharpe + skew + kurtosis. Cornish-Fisher Monte Carlo, percentile distribution of recovery months.
- Methodology: https://aifinhub.io/methodology/drawdown-recovery-markov/

### FTC vs FCA vs MiCA+DORA Regulatory Cost
- URL: https://aifinhub.io/ftc-vs-nlt-regulatory-cost/
- Section: comparators
- Category: Comparators
- Summary: Compare US (FTC), UK (FCA), and EU (MiCA + DORA) compliance cost for an AI-finance product. Snapshot data with as-of date — not legal advice.
- Methodology: https://aifinhub.io/methodology/ftc-vs-nlt-regulatory-cost/

## Benchmarks (2 total)

> Dated, reproducible benchmark reports. Every release publishes methodology + raw data (CSV + JSON) for independent verification.

### State of AI Market Data 2026
- URL: https://aifinhub.io/benchmarks/state-of-ai-market-data-2026/
- Released: 2026-04-20 · Q2 release
- Description: 2026 Q2 baseline for AI-in-markets infrastructure: vendor pricing, MCP grades, LLM per-task cost.
- Raw data CSV: https://aifinhub.io/benchmarks/state-of-ai-market-data-2026/data.csv
- Raw data JSON: https://aifinhub.io/benchmarks/state-of-ai-market-data-2026/data.json

### State of LLM Pricing for Finance Q2 2026
- URL: https://aifinhub.io/benchmarks/state-of-llm-pricing-for-finance-q2-2026/
- Released: 2026-04-23 · Q2 pricing snapshot
- Description: Published vendor pricing for 10 frontier LLMs — Claude, GPT-5, Gemini — with cache, batch, thinking-token, and context-window axes. Four worked cost scenarios.
- Raw data CSV: https://aifinhub.io/benchmarks/state-of-llm-pricing-for-finance-q2-2026/data.csv
- Raw data JSON: https://aifinhub.io/benchmarks/state-of-llm-pricing-for-finance-q2-2026/data.json

## Reference Data (6 total)

> Engine-computed reference surfaces. Each is a parameter sweep of a deterministic engine across a two-axis grid; every cell is real engine output recomputed in CI on every build. Original primary-source data, not a third-party reprint. Each surface ships a CSV download and a schema.org/Dataset record. Education only — not investment advice.

### Kelly Fraction Reference Grid
- URL: https://aifinhub.io/reference/kelly-fraction-grid/
- Engine: https://aifinhub.io/engines/kelly-sizer.js
- Released: 2026-05-23
- Description: Full-Kelly bet fraction across a 7×8 grid of win rate (0.40–0.70) by win/loss payoff ratio (0.5–5.0). 56 cells, each the live output of the kelly-sizer engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: win_rate, win_loss_ratio, full_kelly_fraction, expected_growth_bucket, ruin_probability, median_final_bankroll)

### Options Greeks Delta Reference Grid
- URL: https://aifinhub.io/reference/options-greeks-delta-grid/
- Engine: https://aifinhub.io/engines/options-greeks-explorer.js
- Released: 2026-05-23
- Description: Black–Scholes call delta across an 8×6 grid of strike ($80–$130 on a $100 spot) by implied volatility (10%–60%). 48 cells, each the live output of the options-greeks-explorer engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: strike, vol_pct, delta, gamma, theta_per_day, vega_per_1pct, call_price)

### Edge Variance Kelly Reference Grid
- URL: https://aifinhub.io/reference/edge-variance-kelly-grid/
- Engine: https://aifinhub.io/engines/position-sizing-edge-variance.js
- Released: 2026-05-23
- Description: Variance-adjusted Bayesian fractional Kelly across a 6×5 grid of estimated edge mean (1%–12%) by edge-estimate uncertainty (0.5%–8% stddev). 30 cells, each the live output of the position-sizing-edge-variance engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: edge_mean, edge_stddev, fractional_bayesian_kelly, fractional_deterministic_kelly, fractional_conservative_kelly, cvar_5)

### Token Cost vs Cache Hit Reference Grid
- URL: https://aifinhub.io/reference/token-cost-cache-grid/
- Engine: https://aifinhub.io/engines/token-cost-optimizer.js
- Released: 2026-05-23
- Description: Monthly LLM research-loop cost across a 6×5 grid of input tokens per call (2k–64k) by prompt-cache hit rate (0%–90%), on Claude Sonnet 4.6. 30 cells, each the live output of the token-cost-optimizer engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: input_tokens_per_call, cache_hit_rate, monthly_cost_usd, cost_per_idea_usd, cost_per_validated_trade_usd, effective_cost_per_call_usd)

### Batch vs Realtime Savings Reference Grid
- URL: https://aifinhub.io/reference/batch-savings-grid/
- Engine: https://aifinhub.io/engines/batch-vs-realtime-cost-calculator.js
- Released: 2026-05-23
- Description: Monthly savings from the batch tier vs realtime inference across a 6×5 grid of jobs per day (1k–100k) by output tokens per job (200–4000), on Claude Sonnet 4.6 at a 24h deadline. 30 cells, each the live output of the batch-vs-realtime-cost-calculator engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: jobs_per_day, output_tokens_per_job, savings_per_month_usd, realtime_cost_per_day_usd, batch_cost_per_day_usd, batch_eligible)

### Agent Cost Envelope Reference Grid
- URL: https://aifinhub.io/reference/agent-cost-envelope-grid/
- Engine: https://aifinhub.io/engines/agent-cost-envelope-calculator.js
- Released: 2026-05-23
- Description: Projected monthly agent cost across a 6×6 grid of steps per loop (2–16) by markets analyzed per day (5–200), on Claude Sonnet 4.6. 36 cells, each the live output of the agent-cost-envelope-calculator engine, recomputed in CI. CSV download.
- Raw data CSV: embedded as a data: URI download on the surface page (column headers: steps_per_loop, markets_per_day, cost_per_month_usd, cost_per_day_usd, cost_per_loop_usd, within_budget)

## Research Articles (204 total)

> Long-form research on LLMs in markets. Pillar guides, head-to-head comparisons, runnable tutorials, methodology pieces. Education only, not investment advice.

### The LLM-in-Finance Economics Report 2026
- URL: https://aifinhub.io/articles/llm-in-finance-economics-report-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-26
- Description: LLM-in-finance cost report 2026: every frontier model priced on 10-K extraction, earnings calls, news sentiment, and agents. Engine-computed, verified rates.
- Reading time: 14 min
- Tools referenced: token-cost-optimizer, data-vendor-tco, earnings-call-summarization-cost, sec-filing-chunk-optimizer, model-selector-finance

### Cheapest LLM for SEC 10-K Extraction at 10,000 Filings a Month 2026
- URL: https://aifinhub.io/articles/cheapest-llm-sec-10k-extraction-10000-filings-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Cheapest LLM for SEC 10-K extraction at 10,000 filings/month: Gemini 2.5 Flash-Lite $161.70/mo vs GPT-5.5 $8,715. Engine-computed, with a two-stage path.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Prompt-Caching ROI for Finance LLM Agents 2026
- URL: https://aifinhub.io/articles/prompt-caching-roi-finance-llm-agents-2026/
- Archetype: Methodology · Opinion
- Published: 2026-05-26
- Description: Prompt-caching ROI for finance LLM agents: caching cuts input cost only. Opus 4.7 at 90% cache ($348.48/mo) still loses to uncached Gemini 3.5 Flash.
- Reading time: 9 min
- Tools referenced: token-cost-optimizer, agent-cost-envelope-calculator

### Finance-Workload Cost per 1,000 Tasks: Gemini 3.5 Flash vs Opus 4.7 vs GPT-5.5 2026
- URL: https://aifinhub.io/articles/finance-workload-cost-per-1000-tasks-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Finance-workload cost per 1,000 tasks: Gemini 3.5 Flash $16.50, Opus 4.7 $41.70, GPT-5.5 $55.00, Flash-Lite $1.00. Engine-computed on a verified shape.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Best Python Backtesting Framework 2026
- URL: https://aifinhub.io/articles/best-backtesting-framework-python-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Best Python backtesting framework 2026: VectorBT for research speed, NautilusTrader for live parity, Backtrader for simplicity, Zipline-Reloaded for factors.
- Reading time: 7 min
- Tools referenced: backtest-overfitting-score, walk-forward-validation-visualizer

### VectorBT vs Backtrader 2026
- URL: https://aifinhub.io/articles/vectorbt-vs-backtrader-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: VectorBT vs Backtrader 2026: VectorBT wins research speed and parameter sweeps; Backtrader wins simplicity and the path to live. Which Python backtester fits you.
- Reading time: 6 min
- Tools referenced: backtest-overfitting-score, walk-forward-validation-visualizer

### QuantConnect vs Backtrader 2026
- URL: https://aifinhub.io/articles/quantconnect-vs-backtrader-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: QuantConnect vs Backtrader 2026: hosted platform with bundled data and live deployment versus a free local library with full control. Which backtester fits you.
- Reading time: 6 min
- Tools referenced: backtest-overfitting-score, data-vendor-tco

### Binance vs Coinbase vs Kraken API 2026
- URL: https://aifinhub.io/articles/binance-vs-coinbase-vs-kraken-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Binance vs Coinbase vs Kraken API 2026 for trading bots: Binance wins fees, Coinbase wins US compliance, Kraken balances low fees and WebSocket streaming.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, order-book-replay

### DeepSeek V4 vs Gemini 3.5 Flash: SEC Extraction 2026
- URL: https://aifinhub.io/articles/deepseek-v4-vs-gemini-flash-sec-extraction-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: DeepSeek V4 vs Gemini 3.5 Flash for SEC filing extraction 2026: DeepSeek is ~10x cheaper input, 30x cheaper output with 1M context; Gemini wins ecosystem.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, hallucination-detector

### GPT-5.5 vs Claude Opus 4.7 for Finance 2026
- URL: https://aifinhub.io/articles/gpt-5-5-vs-claude-opus-4-7-finance-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: GPT-5.5 vs Claude Opus 4.7 for finance 2026: same $5 input, Opus edges output at $25 vs $30, but its new tokenizer and 90% caching reshape the real cost.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Qdrant vs Pinecone for Finance RAG 2026
- URL: https://aifinhub.io/articles/qdrant-vs-pinecone-finance-rag-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Qdrant vs Pinecone for financial RAG 2026: close at 10M vectors, but Qdrant self-hosted is far cheaper at 100M and keeps sensitive data under your control.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, sec-filing-chunk-optimizer

### Twelve Data vs EODHD vs FMP 2026
- URL: https://aifinhub.io/articles/twelve-data-vs-eodhd-vs-fmp-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Twelve Data vs EODHD vs FMP 2026: Twelve Data wins real-time streaming, EODHD wins cheap global history, FMP wins fundamentals and SEC filings depth.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, token-cost-optimizer

### Schwab API vs Alpaca 2026
- URL: https://aifinhub.io/articles/schwab-api-vs-alpaca-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Schwab API vs Alpaca 2026: Schwab offers a deeper options chain on a regulated incumbent with OAuth and a 7-day refresh; Alpaca wins simple auth and an MCP server.
- Reading time: 7 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Coinbase vs Kraken API 2026
- URL: https://aifinhub.io/articles/coinbase-vs-kraken-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Coinbase vs Kraken API 2026 for trading bots: Kraken wins fees (~0.25%/0.40% base vs ~0.60%/0.80%); Coinbase wins a simpler per-second rate model.
- Reading time: 6 min
- Tools referenced: data-vendor-tco, order-book-replay

### Binance vs Kraken API 2026
- URL: https://aifinhub.io/articles/binance-vs-kraken-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Binance vs Kraken API 2026: Binance wins fees (~0.075% maker/taker) and ecosystem but is non-US; Kraken is US-regulated with low-latency streaming.
- Reading time: 6 min
- Tools referenced: data-vendor-tco, order-book-replay

### Best Crypto Exchange API for Trading Bots 2026
- URL: https://aifinhub.io/articles/best-crypto-exchange-api-trading-bots-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Best crypto exchange API for trading bots 2026: pick by jurisdiction first. Binance for lowest fees, Coinbase for a US default, Kraken for a lower-fee US venue.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, order-book-replay

### CCXT vs Native Exchange APIs 2026
- URL: https://aifinhub.io/articles/ccxt-vs-native-exchange-apis-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: CCXT vs native exchange APIs 2026: CCXT normalizes 100+ exchanges in one codebase for multi-venue bots; native APIs win feature access and lowest latency.
- Reading time: 7 min
- Tools referenced: order-book-replay, data-vendor-tco

### Zipline-Reloaded vs Backtrader 2026
- URL: https://aifinhub.io/articles/zipline-vs-backtrader-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Zipline-Reloaded vs Backtrader 2026: Zipline-Reloaded is the maintained fork with a Pipeline API for equity factor research; Backtrader is flexible but aging.
- Reading time: 7 min
- Tools referenced: backtest-overfitting-score, walk-forward-validation-visualizer

### NautilusTrader vs VectorBT 2026
- URL: https://aifinhub.io/articles/nautilustrader-vs-vectorbt-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: NautilusTrader vs VectorBT 2026: NautilusTrader is a Rust-cored engine with research-to-live parity; VectorBT is the fastest vectorized research library.
- Reading time: 7 min
- Tools referenced: backtest-overfitting-score, walk-forward-validation-visualizer

### GPT-5.5 vs Gemini 3.5 Flash for Finance 2026
- URL: https://aifinhub.io/articles/gpt-5-5-vs-gemini-3-5-flash-finance-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: GPT-5.5 vs Gemini 3.5 Flash for finance 2026: GPT-5.5 ($5/$30) is frontier reasoning; Gemini 3.5 Flash ($1.50/$9) is an agent-tier workhorse, ~3.3x cheaper.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Self-Hosted vs API LLM for Finance: Breakeven 2026
- URL: https://aifinhub.io/articles/self-hosted-vs-api-llm-finance-breakeven-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Self-hosted vs API LLM for finance 2026: a rented H100 (~$1.50-$7/hr) only beats per-token APIs at high volume. Idle time and ops make it 3-5x the raw GPU cost.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### EODHD vs Financial Modeling Prep (FMP) 2026
- URL: https://aifinhub.io/articles/eodhd-vs-fmp-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: EODHD vs FMP 2026: EODHD wins transparent, cheap global EOD pricing ($19.99/mo); FMP wins fundamentals and filings depth with a 250-requests/day free tier.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, token-cost-optimizer

### Twelve Data vs Polygon.io (now Massive) 2026
- URL: https://aifinhub.io/articles/twelve-data-vs-polygon-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Twelve Data vs Polygon.io (now Massive) 2026: Twelve Data wins multi-asset breadth (stocks/forex/crypto); Polygon wins granular US equities/options tick depth.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, order-book-replay

### sec-api.io vs SEC EDGAR Free API 2026
- URL: https://aifinhub.io/articles/sec-api-vs-edgar-free-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: sec-api.io vs the free SEC EDGAR API 2026: EDGAR is free, keyless, 10 req/sec, raw filings; sec-api.io ($55-$239/mo) adds search and section extractors.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, sec-filing-chunk-optimizer

### Tradier vs Alpaca for Options 2026
- URL: https://aifinhub.io/articles/tradier-vs-alpaca-options-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Tradier vs Alpaca for options 2026: Tradier is options-first with real-time chains and multi-leg orders; Alpaca wins simple auth and an MCP server.
- Reading time: 7 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Is Databento Worth It in 2026?
- URL: https://aifinhub.io/articles/is-databento-worth-it-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Is Databento worth it in 2026? For builders needing pro-grade, granular data without a contract, usually yes; for casual retail, often no. Usage-based pricing.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, order-book-replay

### Is Polygon (Massive) Pricing Worth It in 2026?
- URL: https://aifinhub.io/articles/polygon-massive-pricing-worth-it-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Is Polygon (now Massive) pricing worth it in 2026? Stocks: free Basic, $29/$79 delayed, $199 Advanced for real-time SIP. Real-time costs more than expected.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, order-book-replay

### Best Free Stock Market Data API 2026
- URL: https://aifinhub.io/articles/best-free-stock-market-data-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-26
- Description: Best free stock market data API 2026: Alpaca's IEX tier for real-time US equities, SEC EDGAR for fundamentals, Twelve Data and EODHD for breadth.
- Reading time: 8 min
- Tools referenced: data-vendor-tco, token-cost-optimizer

### Alpaca API Rate Limits 2026
- URL: https://aifinhub.io/articles/alpaca-api-rate-limits-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Alpaca API rate limits 2026: Trading API 200 req/min (paper and live), Market Data 200 req/min free IEX or 10,000 on Algo Trader Plus. Verified, with geo notes.
- Reading time: 6 min
- Tools referenced: broker-api-comparator

### Alpaca API Free Tier: IEX vs SIP 2026
- URL: https://aifinhub.io/articles/alpaca-iex-vs-sip-free-tier-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Alpaca free tier is the IEX feed (~3% of US volume); the paid SIP feed (Algo Trader Plus, $99/mo) is the full tape. What each is valid for, verified.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Alpaca vs Interactive Brokers API Comparison 2026
- URL: https://aifinhub.io/articles/alpaca-vs-interactive-brokers-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Alpaca vs Interactive Brokers API comparison 2026: Alpaca wins on REST/JSON ergonomics, IBKR on multi-asset coverage. Verified rate limits and fees.
- Reading time: 8 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Alpaca vs Tradier API 2026
- URL: https://aifinhub.io/articles/alpaca-vs-tradier-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Alpaca vs Tradier API 2026: Alpaca wins on free IEX data and 200 req/min trading; Tradier on options-first depth at 60 req/min trading. Verified limits.
- Reading time: 7 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Alpha Vantage vs Twelve Data 2026
- URL: https://aifinhub.io/articles/alpha-vantage-vs-twelve-data-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Alpha Vantage vs Twelve Data 2026: verified free-tier limits, paid plan prices, and per-minute rate caps. Twelve Data wins free use; paid pick depends on scan.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Benzinga News API Pricing 2026
- URL: https://aifinhub.io/articles/benzinga-news-api-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Benzinga News API pricing 2026: sales-gated premium tiers, a fee-free Basic tier, and why Polygon.io's bundled Ticker News is the cheaper self-serve option.
- Reading time: 6 min
- Tools referenced: finance-mcp-directory, data-vendor-tco

### Best LLM for Financial Analysis 2026
- URL: https://aifinhub.io/articles/best-llm-for-financial-analysis-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best LLM for financial analysis in 2026 is task-tiered: Gemini Flash for extraction, Gemini Pro for long context, Opus 4.7 or GPT-5.5 for reasoning.
- Reading time: 9 min
- Tools referenced: model-selector-finance, token-cost-optimizer

### Cheapest LLM for SEC Filings 2026
- URL: https://aifinhub.io/articles/cheapest-llm-for-sec-filings-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Cheapest LLM for SEC filings 2026: verified prices and cost per 10-K for Gemini Flash, DeepSeek, GPT-5.4 nano, and Haiku. Context fit and accuracy decide it.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Cheapest Stock Market Data API 2026
- URL: https://aifinhub.io/articles/cheapest-stock-market-data-api-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Cheapest stock market data API 2026: Alpaca IEX is the free floor, Finnhub the best free rate limit, Alpaca SIP $99 the cheapest real-time tape. Verified.
- Reading time: 8 min
- Tools referenced: data-vendor-tco, finance-mcp-directory

### Claude vs GPT-5 vs Gemini for Financial Analysis 2026
- URL: https://aifinhub.io/articles/claude-vs-gpt5-vs-gemini-finance-pricing-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Claude vs GPT-5 vs Gemini for financial analysis 2026: verified API list prices, context windows, caching discounts, and effective cost per 10-K filing.
- Reading time: 7 min
- Tools referenced: model-selector-finance, token-cost-optimizer

### Databento vs Polygon.io 2026
- URL: https://aifinhub.io/articles/databento-vs-polygon-io-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Databento vs Polygon.io 2026: metered $/GB with $125 free credits vs Polygon's flat $199/mo real-time tier. Level-2 depth, predictability, and who wins.
- Reading time: 7 min
- Tools referenced: data-vendor-tco

### DeepSeek vs Mistral for Financial Analysis 2026
- URL: https://aifinhub.io/articles/deepseek-vs-mistral-finance-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: DeepSeek vs Mistral for financial analysis 2026: verified DeepSeek V4 pricing and context, Mistral's lineup, and the per-loop agent economics that decide cost.
- Reading time: 7 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer

### EODHD vs Marketstack 2026
- URL: https://aifinhub.io/articles/eodhd-vs-marketstack-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: EODHD vs Marketstack 2026: verified plan prices, request quotas, and global coverage. EODHD wins deep global EOD; Marketstack's Basic is the cheaper thin entry.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Is Finnhub Free? Free Tier Limits 2026
- URL: https://aifinhub.io/articles/finnhub-free-tier-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Is Finnhub free in 2026? Yes, a free tier with a documented 60 calls/minute, real-time US quotes, and 50-symbol WebSocket. Free vs paid and commercial catch.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### IBKR TWS API Rate Limits 2026
- URL: https://aifinhub.io/articles/ibkr-tws-api-rate-limits-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: IBKR TWS API rate limits 2026: 50 messages/second client cap, historical pacing (60 per 10 min, 6 per 2s), 100 data lines, the option-chain throttle. Verified.
- Reading time: 7 min
- Tools referenced: broker-api-comparator

### Interactive Brokers API Pricing 2026
- URL: https://aifinhub.io/articles/interactive-brokers-api-pricing-rate-limits-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Interactive Brokers API pricing 2026: the API is free (commission-based), market data $1-15/mo per exchange, TWS API capped at 50 messages/second. Verified.
- Reading time: 7 min
- Tools referenced: broker-api-comparator

### OpenAI Prompt Caching Pricing 2026
- URL: https://aifinhub.io/articles/openai-prompt-caching-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: OpenAI prompt caching pricing 2026: cached input is 10% of standard (GPT-5.5 $0.50 vs $5.00), automatic and prefix-based. Anthropic compared. Verified.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### Polygon.io Free Tier Limits 2026
- URL: https://aifinhub.io/articles/polygon-io-free-tier-limits-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Polygon.io free tier limits 2026: 5 API calls/minute, 15-minute delayed data, ~2 years of history, no WebSocket. Every Basic-plan constraint, verified.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Polygon.io Futures API Pricing 2026
- URL: https://aifinhub.io/articles/polygon-io-futures-forex-api-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Polygon.io futures API pricing 2026: Futures free Basic to $199 Advanced (real-time CME group), Currencies $49 Starter for real-time forex. Verified.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, trading-system-blueprinter

### Polygon.io News API Pricing 2026
- URL: https://aifinhub.io/articles/polygon-io-news-api-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Polygon.io news API pricing 2026: the Ticker News endpoint is free on every tier with sentiment fields; free Basic caps history at 2 years. Verified.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, finance-mcp-directory

### Polygon.io Options API Pricing 2026
- URL: https://aifinhub.io/articles/polygon-io-options-data-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Polygon.io options API pricing 2026: Starter $29, Developer $79, Advanced $199. Greeks and IV on every paid tier; only Advanced is real-time. Verified.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Polygon.io Pricing Plans 2026
- URL: https://aifinhub.io/articles/polygon-io-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Polygon.io pricing plans 2026: Basic is free (5 calls/min), Starter $29, Developer $79, Advanced $199 for real-time SIP. Every tier verified.
- Reading time: 7 min
- Tools referenced: data-vendor-tco

### Robinhood API: Official or Unofficial 2026
- URL: https://aifinhub.io/articles/robinhood-api-official-unofficial-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Robinhood API official or unofficial 2026: the Crypto Trading API is real and key-based, but there is no official stock or options API. What to use instead.
- Reading time: 6 min
- Tools referenced: broker-api-comparator

### Charles Schwab thinkorswim API for Automated Trading 2026
- URL: https://aifinhub.io/articles/schwab-thinkorswim-api-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Charles Schwab thinkorswim API for automated trading 2026: there is no standalone thinkorswim API; all automation routes through the Schwab Trader API.
- Reading time: 7 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Charles Schwab Trader API Status 2026
- URL: https://aifinhub.io/articles/schwab-trader-api-status-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Charles Schwab Trader API status 2026: live for individual developers, 1-3 day approval, 120 req/min limit. TD Ameritrade shutdown and thinkorswim, verified.
- Reading time: 7 min
- Tools referenced: broker-api-comparator

### SEC EDGAR API Rate Limits 2026
- URL: https://aifinhub.io/articles/sec-edgar-api-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: SEC EDGAR API rate limits 2026: 10 requests/second per requester, free with no API key, User-Agent header required. Endpoints, bulk data, and pipeline guidance.
- Reading time: 7 min
- Tools referenced: finance-mcp-directory

### Tiingo vs Polygon vs Finnhub 2026
- URL: https://aifinhub.io/articles/tiingo-vs-polygon-vs-finnhub-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Tiingo vs Polygon vs Finnhub 2026: Tiingo wins on fundamentals, Finnhub on its free tier (60 calls/min), Polygon on flat-rate intraday. Verified prices.
- Reading time: 8 min
- Tools referenced: data-vendor-tco, finance-mcp-directory

### TradeStation API Pricing 2026
- URL: https://aifinhub.io/articles/tradestation-api-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: TradeStation API pricing 2026: a funded account plus an email request gets a WebAPI key; rate limits are per-category. Verified access and limits.
- Reading time: 7 min
- Tools referenced: broker-api-comparator, trading-system-blueprinter

### Tradier API Rate Limits 2026
- URL: https://aifinhub.io/articles/tradier-api-rate-limits-pricing-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Tradier API rate limits 2026: 120 req/min market data, 60 req/min order placement, 60 in sandbox. X-Ratelimit headers, options-first capabilities, verified.
- Reading time: 6 min
- Tools referenced: broker-api-comparator

### CoinGecko vs CoinMarketCap API 2026
- URL: https://aifinhub.io/articles/coingecko-vs-coinmarketcap-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: CoinGecko vs CoinMarketCap API 2026: free Demo 10k calls at 100/min vs Basic 15k credits at 50/min, plus paid plans. Calls vs credits, and who wins.
- Reading time: 6 min
- Tools referenced: finance-mcp-directory

### Intrinio vs Polygon.io 2026
- URL: https://aifinhub.io/articles/intrinio-vs-polygon-io-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Intrinio vs Polygon.io 2026: institution-priced per-product feeds from $1,250/mo vs Polygon's flat $199/mo real-time retail tier. Who wins, and when.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Tradier vs Tastytrade API 2026
- URL: https://aifinhub.io/articles/tradier-vs-tastytrade-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Tradier vs Tastytrade API 2026: Tradier's published 120/60 req/min limits vs Tastytrade's OAuth Open API, 24h sandbox, and DXLink streaming. Who wins.
- Reading time: 6 min
- Tools referenced: broker-api-comparator, finance-mcp-directory

### Schwab Developer API vs IBKR 2026
- URL: https://aifinhub.io/articles/schwab-developer-api-vs-ibkr-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Schwab Developer API vs IBKR 2026: Schwab's 120 req/min OAuth REST vs IBKR's free pacing-based TWS API. Cost, rate models, and multi-asset breadth.
- Reading time: 6 min
- Tools referenced: broker-api-comparator

### TradeStation API vs Alpaca 2026
- URL: https://aifinhub.io/articles/tradestation-api-vs-alpaca-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: TradeStation API vs Alpaca 2026: TradeStation's funded-account key gate and per-category limits vs Alpaca's instant free key and flat 200 req/min.
- Reading time: 6 min
- Tools referenced: broker-api-comparator

### Polygon.io vs Alpaca Market Data 2026
- URL: https://aifinhub.io/articles/polygon-io-vs-alpaca-market-data-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Polygon.io vs Alpaca market data 2026: Alpaca's free IEX feed and $99/mo full SIP vs Polygon's $199/mo unlimited-call real-time tier. Who wins.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Financial Modeling Prep vs Alpha Vantage 2026
- URL: https://aifinhub.io/articles/financial-modeling-prep-vs-alpha-vantage-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Financial Modeling Prep vs Alpha Vantage 2026: FMP's 250/day free tier and fundamentals depth vs Alpha Vantage's rate-tiered premium plans. Who wins.
- Reading time: 6 min
- Tools referenced: data-vendor-tco

### Best Crypto Market Data APIs 2026
- URL: https://aifinhub.io/articles/best-crypto-market-data-apis-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Best crypto market data APIs 2026: CoinGecko Demo for prototyping, CoinMarketCap Hobbyist for the cheapest paid step, Twelve Data for multi-asset agents.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, finance-mcp-directory

### Best Fundamental & Filings Data APIs for Finance 2026
- URL: https://aifinhub.io/articles/best-fundamental-filings-data-apis-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Best fundamental and filings data APIs 2026: FMP for free-tier headroom, EODHD for global breadth, Alpha Vantage for clear pricing, Intrinio for feeds.
- Reading time: 7 min
- Tools referenced: data-vendor-tco

### Best Free LLM Token-Cost Calculator for Finance 2026
- URL: https://aifinhub.io/articles/best-free-llm-token-cost-calculator-finance-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Best free LLM token-cost calculator for finance 2026: the Token-Cost Optimizer prices a research loop per validated trade, compared with alternatives.
- Reading time: 6 min
- Tools referenced: token-cost-optimizer

### Gemini 3.5 Flash for Financial Agents: The Cost Reality 2026
- URL: https://aifinhub.io/articles/gemini-3-5-flash-financial-agents-cost-reality-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Gemini 3.5 Flash for financial agents 2026: at $1.50/$9.00 it is frontier agent-tier at Flash speed, not budget. Real loop cost vs Flash-Lite, Opus.
- Reading time: 7 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer

### Gemini 3.5 Flash vs GPT-5.5 vs Claude Opus 4.7 for Finance Extraction 2026
- URL: https://aifinhub.io/articles/gemini-3-5-flash-vs-gpt5-5-vs-opus-finance-extraction-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Gemini 3.5 Flash vs GPT-5.5 vs Opus 4.7 for 10-K extraction 2026: verified per-filing cost from the engine. Cheapest frontier pick, not budget.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, model-selector-finance

### The 2026 Gemini Cost Ladder for Finance: 3.5 Flash, Flash-Lite, 2.5 Pro
- URL: https://aifinhub.io/articles/2026-gemini-cost-ladder-finance/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Gemini 3.5 Flash, Flash-Lite, 2.5 Pro for finance 2026: a verified three-rung cost ladder from the engine. 3.5 Flash sits at the top, not the floor.
- Reading time: 6 min
- Tools referenced: token-cost-optimizer, agent-cost-envelope-calculator

### Best LLM APIs for SEC Filing Extraction 2026
- URL: https://aifinhub.io/articles/best-llm-apis-sec-filing-extraction-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best LLM APIs for SEC filing extraction 2026 ranked on price, context window, and numeric fidelity: Gemini Flash for volume, Claude and GPT for tables.
- Reading time: 9 min
- Tools referenced: model-selector-finance, token-cost-optimizer, sec-filing-chunk-optimizer

### Best Real-Time Options Data APIs 2026
- URL: https://aifinhub.io/articles/best-real-time-options-data-apis-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best real-time options data APIs 2026: Tradier free to account holders, Alpaca at $99, Polygon, Databento OPRA, Cboe LiveVol. Verified vendor pricing.
- Reading time: 9 min
- Tools referenced: broker-api-comparator, data-vendor-tco, options-greeks-explorer

### Best Sentiment & News APIs for Trading 2026
- URL: https://aifinhub.io/articles/best-sentiment-news-apis-trading-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best sentiment and news APIs for trading 2026: Finnhub free 60 calls/min, Alpha Vantage AI scores, Polygon news, Benzinga wire. Verified vendor pricing.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, prompt-injection-tester, hallucination-detector

### Best Backtesting Data Sources 2026
- URL: https://aifinhub.io/articles/best-backtesting-data-sources-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best backtesting data sources 2026: Alpaca free IEX, Polygon flat files, Databento tick history, Nasdaq Data Link, plus the survivorship trap.
- Reading time: 9 min
- Tools referenced: data-vendor-tco, synthetic-market-data-generator, backtest-overfitting-score

### Best Free Market-Data Cost Calculator 2026
- URL: https://aifinhub.io/articles/best-free-market-data-cost-calculator-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Best free market-data cost calculator 2026: the Data-Vendor TCO tool gates vendors on coverage and ranks the qualifying ones cheapest-first.
- Reading time: 8 min
- Tools referenced: data-vendor-tco

### Binance vs Coinbase API 2026
- URL: https://aifinhub.io/articles/binance-vs-coinbase-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: Binance vs Coinbase Advanced Trade API 2026: Binance meters 6,000 request-weight/min per IP, Coinbase 30 req/s per user. Verified rate limits.
- Reading time: 7 min
- Tools referenced: finance-mcp-directory, kalshi-poly-arb

### EODHD vs Tiingo API 2026
- URL: https://aifinhub.io/articles/eodhd-vs-tiingo-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-25
- Description: EODHD vs Tiingo 2026: EODHD covers 150,000+ global tickers from €19.99/mo with documented limits; Tiingo is a cheaper US-focused EOD bundle.
- Reading time: 7 min
- Tools referenced: data-vendor-tco

### Best Vector DBs for Financial RAG 2026
- URL: https://aifinhub.io/articles/best-vector-dbs-financial-rag-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-25
- Description: Best vector databases for financial RAG 2026: pgvector free on Postgres, Qdrant Cloud free-forever tier, Pinecone serverless, Weaviate. Verified pricing.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, sec-filing-chunk-optimizer, hallucination-detector

### 10-K Token Estimator: Cache Hit Rate as the Cost Driver
- URL: https://aifinhub.io/articles/10k-token-estimator-cache-design/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine output across 10 models and 3 cache regimes: Sonnet at 60% cache costs $0.144 per 10-K with peers; cache architecture drives cost more than model.
- Reading time: 11 min
- Tools referenced: financial-document-token-estimator, token-cost-optimizer, sec-filing-chunk-optimizer

### Agent Cost Envelope: 150 Markets a Day, Three Configurations
- URL: https://aifinhub.io/articles/agent-cost-envelope-150-markets/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns Sonnet at 60% convergence = $859/month for 150 markets × 5 steps — 1.72× over budget. Opus is 5× higher; steps are the binding constraint.
- Reading time: 10 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer, model-selector-finance

### Alpaca vs Tradier: Options + MCP Coverage Compared
- URL: https://aifinhub.io/articles/alpaca-vs-tradier-options-mcp-coverage/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Comparator returns Alpaca as the only strict-filter fit (4/4); Tradier ties when auth relaxes. MCP directory confirms one official broker MCP.
- Reading time: 11 min
- Tools referenced: broker-api-comparator, finance-mcp-directory, trading-system-blueprinter

### Auditable LLM Decision-Making for Finance
- URL: https://aifinhub.io/articles/auditable-llm-decision-making-finance/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: Six load-bearing audit layers mapped to MiCA, MiFID II, SEC 17a-4, FINRA 4511, SR 11-7, BaFin MaRisk. Collapsing any layer destroys defensibility.
- Reading time: 13 min
- Tools referenced: hallucination-detector, structured-schema-validator-finance, ftc-vs-nlt-regulatory-cost

### Batch vs Realtime Overnight Cost
- URL: https://aifinhub.io/articles/batch-vs-realtime-overnight-cost/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: A 12-hour deadline kills the batch discount. On 5,000 jobs at Sonnet 4.6, real-time is €210/day; batch would be €105 but the 24h SLA blocks it.
- Reading time: 6 min
- Tools referenced: batch-vs-realtime-cost-calculator, token-cost-optimizer, fallback-chain-simulator

### Calibration Dojo vs Platt vs Isotonic: The Right Tool
- URL: https://aifinhub.io/articles/calibration-dojo-vs-platt-vs-isotonic/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Engine: Brier 0.202, reliability 0.009 on a 200-forecast sample tape (well calibrated). Three calibration methods address different LLM-output failure modes.
- Reading time: 12 min
- Tools referenced: calibration-dojo, forecast-scoring-sandbox, kelly-sizer

### Claude Opus 4.7 vs Gemini 2.5 Pro: 10-K Extraction Cost
- URL: https://aifinhub.io/articles/claude-opus-vs-gemini-pro-extraction-cost/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Engine output: Opus $0.66 vs Gemini Pro $0.06 per 2-peer 10-K synthesis (10.6× ratio). Selector ties them at score 98; the eval-harness pivots on quality.
- Reading time: 11 min
- Tools referenced: financial-document-token-estimator, model-selector-finance, token-cost-optimizer

### Claude Sonnet vs GPT-5 on Prompt Cache for Finance
- URL: https://aifinhub.io/articles/claude-sonnet-vs-gpt5-on-prompt-cache-finance/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Claude Sonnet's 5-minute TTL gives 90% off cached reads ($0.30/M); GPT-5's token cache gives 50% off a $10/M base ($5/M). Sonnet wins on cost; GPT-5's edge is cache survival.
- Reading time: 7 min
- Tools referenced: token-cost-optimizer, financial-document-token-estimator, model-selector-finance

### Data Vendor TCO for EU Retail
- URL: https://aifinhub.io/articles/data-vendor-tco-for-eu-retail/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Alpaca Algo Trader Plus is €1,188/year on headline. OPRA pass-through, exchange fees, and BaFin record-keeping push true TCO to €2,400-3,800.
- Reading time: 7 min
- Tools referenced: data-vendor-tco, broker-api-comparator, trading-system-blueprinter

### Deflated Sharpe in Low-Trial Research Programmes
- URL: https://aifinhub.io/articles/deflated-sharpe-low-trial-regimes/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine output on a 1.8 Sharpe at trial counts 1, 40, 100, 1000 — selection-bias benchmark grows fast; low-trial regimes do not protect raw Sharpe.
- Reading time: 11 min
- Tools referenced: deflated-sharpe-ratio, backtest-overfitting-score, risk-adjusted-returns

### Deflated Sharpe vs PBO on the Same Tape
- URL: https://aifinhub.io/articles/deflated-sharpe-vs-pbo-on-the-same-tape/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Engine output on 8 strategies: PBO = 0.726 (over the 0.5 overfit threshold) and DSR PSR = 0. Two tests reject the tape for different reasons.
- Reading time: 11 min
- Tools referenced: deflated-sharpe-ratio, backtest-overfitting-score, walk-forward-validator

### Drawdown Markov: Recovery Tails Explained
- URL: https://aifinhub.io/articles/drawdown-markov-and-recovery-tail/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Canonical input yields p95 = 39 months recovery on a 25% drawdown threshold — the kill-switch parameter most backtest reports omit entirely.
- Reading time: 11 min
- Tools referenced: drawdown-recovery-markov, returns-distribution-analyzer, risk-adjusted-returns

### Drawdown Markov vs Historical Bootstrap: Tape-Length Decision
- URL: https://aifinhub.io/articles/drawdown-markov-vs-historical-bootstrap/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Engine returns p95 recovery 28 months on canonical input; Markov beats bootstrap on tapes under 60 months and loses on tapes over 240 months.
- Reading time: 11 min
- Tools referenced: drawdown-recovery-markov, returns-distribution-analyzer, var-backtest-kupiec-christoffersen

### Earnings Call Summarization: 250 Tickers, Nine Models
- URL: https://aifinhub.io/articles/earnings-call-summarization-cost-tickers/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns $0.91/year (Gemini 2.5 Flash-Lite) to $42.80/year (Opus 4.7) for 250-ticker quarterly coverage. Operator review time dominates API spend by 200×.
- Reading time: 9 min
- Tools referenced: earnings-call-summarization-cost, financial-document-token-estimator, model-selector-finance

### Edge-Variance Sizing for LLM Signals
- URL: https://aifinhub.io/articles/edge-variance-sizing-for-llm-signals/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Deterministic Kelly on a 2.5% edge says 55.6% of bankroll. The conservative lower-bound posterior says 15.6%. For LLM signals, conservative wins.
- Reading time: 6 min
- Tools referenced: position-sizing-edge-variance, kelly-sizer, calibration-dojo

### LLM Finance Error Taxonomy: The Bond-Yield Trap
- URL: https://aifinhub.io/articles/error-taxonomy-bond-yield-trap/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: A 12-mode taxonomy of LLM finance errors. Coupon-yield conflation is the textbook case. A 30-line classifier catches 70-80% before they ship.
- Reading time: 7 min
- Tools referenced: llm-finance-error-taxonomy, hallucination-detector, prompt-regression-tester

### Execution Simulator: 50k Shares at 10% Participation
- URL: https://aifinhub.io/articles/execution-simulator-10pct-participation/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns 12.59 bps total cost ($2,833 on $2.25M notional) for a 50k-share buy at 10% participation. Splitting across days makes impact worse.
- Reading time: 10 min
- Tools referenced: execution-simulator, order-book-replay, statistical-arbitrage-capacity

### Execution Simulator vs Order Book Replay
- URL: https://aifinhub.io/articles/execution-simulator-vs-orderbook-replay/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Simulator: parametric impact, fast, sometimes wrong. Replay: actual book snapshots, true slippage, needs data. Replay is the honest tool at scale.
- Reading time: 7 min
- Tools referenced: order-book-replay, execution-simulator, data-vendor-tco

### Fallback Chain Simulation: When Claude Is Down
- URL: https://aifinhub.io/articles/fallback-chain-simulation-claude-down/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Single-provider uptime ~99.5%. A two-stage Anthropic→OpenAI chain lifts it to 99.99%. The fallback returns an answer, not a matching answer.
- Reading time: 7 min
- Tools referenced: fallback-chain-simulator, token-cost-optimizer, agent-cost-envelope-calculator

### First Principles: LLMs and Market Microstructure
- URL: https://aifinhub.io/articles/first-principles-llm-microstructure/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: LLMs cannot reason about sub-millisecond mechanics. They are useful for literature synthesis, slippage post-mortems, and hypothesis generation only.
- Reading time: 9 min
- Tools referenced: execution-simulator, order-book-replay, trading-system-blueprinter

### Forecast Scoring Sandbox: Reading the Reliability Curve
- URL: https://aifinhub.io/articles/forecast-scoring-sandbox-reliability-curve/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: 15 forecasts: Brier 0.154, log-loss 0.470. Murphy decomposition shows reliability equals uncertainty — informative but mis-calibrated forecaster.
- Reading time: 7 min
- Tools referenced: forecast-scoring-sandbox, calibration-dojo, hallucination-detector

### FTC vs NLT Regulatory Cost for EU Publishing
- URL: https://aifinhub.io/articles/ftc-nlt-regulatory-cost-eu-publishing/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: FTC-supervised finance publishing runs €88,440/year. The no-licence alternative cuts that by half. EU adds BaFin and MiFID II overhead on top.
- Reading time: 7 min
- Tools referenced: ftc-vs-nlt-regulatory-cost, agent-cost-envelope-calculator, trading-system-blueprinter

### FTC vs BaFin: Publishing Rule Cost Compared
- URL: https://aifinhub.io/articles/ftc-vs-bafin-publishing-rule-cost/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: The regulatory-cost engine returns US-FTC $42,360/year vs EU MiCA+DORA $179,600 at the same operating shape. BaFin, MAR, and AI Act add publishing layers the engine does not price.
- Reading time: 7 min
- Tools referenced: ftc-vs-nlt-regulatory-cost, trading-system-blueprinter, agent-cost-envelope-calculator

### Hallucination Detector: Numeric Source Grounding in Practice
- URL: https://aifinhub.io/articles/hallucination-detector-numeric-source-grounding/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine flags an EPS substitution ($0.81 vs source $0.78) at groundingRate 0.25 — the substitution failure semantic-similarity checks systematically miss.
- Reading time: 10 min
- Tools referenced: hallucination-detector, structured-schema-validator-finance, price-blind-auditor

### Kelly vs Fixed Fractional on a Noisy Edge
- URL: https://aifinhub.io/articles/kelly-vs-fixed-fractional-on-noisy-edge/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: On a p=0.55, b=1.40 edge, capped Kelly (3%) returns a 14.5x median vs fixed 2%'s 6.2x; fixed fractional wins on drawdown and noisy-edge robustness.
- Reading time: 7 min
- Tools referenced: kelly-sizer, position-sizing-edge-variance, drawdown-recovery-markov

### Kelly with Uncertain Edge: Quarter vs Eighth
- URL: https://aifinhub.io/articles/kelly-with-uncertain-edge-quarter-vs-eighth/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Quarter-Kelly assumes you know win-rate. When it is a Beta posterior, eighth-Kelly often dominates on long-run growth and on path-of-ruin probability.
- Reading time: 7 min
- Tools referenced: kelly-sizer, position-sizing-edge-variance, calibration-dojo

### Kupiec vs Bootstrap for VaR Validation
- URL: https://aifinhub.io/articles/kupiec-vs-bootstrap-var-validation/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: 30-day VaR backtest: 7 exceptions vs 0.3 expected, Kupiec LR 32.34, p 1.3e-8. Bootstrap agrees but converges slower. Basel III names Kupiec.
- Reading time: 7 min
- Tools referenced: var-backtest-kupiec-christoffersen, returns-distribution-analyzer, synthetic-market-data-generator

### Model Risk Management for Solo LLM Research Loops
- URL: https://aifinhub.io/articles/model-risk-management-llm-research-loops/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: Federal Reserve SR 11-7's three-lines-of-defence framework adapted for the single-operator LLM workflow. Ignoring it re-invents prevented failures.
- Reading time: 12 min
- Tools referenced: model-selector-finance, hallucination-detector, fallback-chain-simulator

### Model Selector: Extraction Tier at $50 / sub-5s / Medium
- URL: https://aifinhub.io/articles/model-selector-finance-extraction-tier/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns Gemini 2.5 Flash-Lite (score 96.0, $3/mo) as the top qualifying model, with Gemini 2.5 Flash second; Haiku 4.5 disqualified on context window, Sonnet+ on budget.
- Reading time: 10 min
- Tools referenced: model-selector-finance, token-cost-optimizer, financial-document-token-estimator

### Operational Risk for Solo Quant Stacks
- URL: https://aifinhub.io/articles/operational-risk-for-solo-quant-stacks/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: Basel's seven operational-risk categories applied to a single-operator launchd stack. Categories 6 and 7 dominate solo-quant losses by an order.
- Reading time: 12 min
- Tools referenced: trading-system-blueprinter, fallback-chain-simulator, hallucination-detector

### Options Greeks: 30-DTE OTM Call, Worked End to End
- URL: https://aifinhub.io/articles/options-greeks-30dte-otm-call-walkthrough/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns delta 0.301, gamma 0.0217, theta −$0.10/day, vega $0.20/IV-point for a 30-DTE 5% OTM call on $200 spot at 28% IV — the LLM-confounder case.
- Reading time: 11 min
- Tools referenced: options-greeks-explorer, options-payoff-builder, hallucination-detector

### PBO Score on an Eight-Strategy Matrix
- URL: https://aifinhub.io/articles/pbo-score-on-eight-strategy-matrix/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Eight synthetic strategies on 80 observations: PBO = 0, deflated Sharpe = 0 for every candidate. The combination is uninformative when correlated.
- Reading time: 6 min
- Tools referenced: backtest-overfitting-score, deflated-sharpe-ratio, walk-forward-validator

### Prompt Injection Tester: News Feed Agents
- URL: https://aifinhub.io/articles/prompt-injection-tester-news-feed/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: 23 attack payloads against a finance research agent reading attacker-controlled news. Typical first run: 4-7 vulnerable patterns. Four mitigations.
- Reading time: 7 min
- Tools referenced: prompt-injection-tester, hallucination-detector, agent-skill-tester

### Publishing Finance Content with LLMs in the EU
- URL: https://aifinhub.io/articles/publishing-finance-content-with-llms-eu/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: An EU publisher using LLMs sits between BaFin/WpHG, MiCA, EU AI Act, and ESMA. The defensible posture: no advice, disclose AI, publish methodology.
- Reading time: 9 min
- Tools referenced: ftc-vs-nlt-regulatory-cost, trading-system-blueprinter, llm-finance-error-taxonomy

### Returns Distribution: Fat Tails in an Equity Portfolio
- URL: https://aifinhub.io/articles/returns-distribution-fat-tails-equity-pf/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: 55-month sample. Skew -0.54, JB p-value 0.24. Normality test fails to reject — the QQ tail still shows the distribution is fat enough to break VaR.
- Reading time: 7 min
- Tools referenced: returns-distribution-analyzer, var-backtest-kupiec-christoffersen, position-sizing-edge-variance

### Risk-Adjusted Returns: Benchmark Choice Drives the Report
- URL: https://aifinhub.io/articles/risk-adjusted-returns-benchmark-selection/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns IR 0.708 vs 0.433 and beta 1.246 vs 3.054 on the same returns against two benchmarks. Sharpe is invariant; alpha and IR are not.
- Reading time: 10 min
- Tools referenced: risk-adjusted-returns, correlation-matrix-visualizer, efficient-frontier-builder

### Risk Parity vs Efficient Frontier: 3-Asset Portfolio Build
- URL: https://aifinhub.io/articles/risk-parity-vs-efficient-frontier-portfolio/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: Engine returns a reported tangency [12%, −40%, 85%, 42%] and min-variance [8%, 8%, 79%, 6%] on a four-asset macro tape; risk parity refuses the short. Decision pivot.
- Reading time: 12 min
- Tools referenced: efficient-frontier-builder, correlation-matrix-visualizer, risk-adjusted-returns

### Schema Validator: Trade Decision Strictness in Practice
- URL: https://aifinhub.io/articles/schema-validator-trade-decision-strictness/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine: 4 payloads against trade_decision — pass, missing-fields fail, sanity-banded warning, enum-mismatch fail. Strict mode is the safe default.
- Reading time: 10 min
- Tools referenced: structured-schema-validator-finance, hallucination-detector, prompt-injection-tester

### SEC Filing Chunking: Strategy, Size, and Embedding Cost
- URL: https://aifinhub.io/articles/sec-chunking-overlap-tradeoff/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns 131 chunks at 1024-tok/10% overlap on a 10-K body; structural preserves table boundaries that recursive splits across six runs.
- Reading time: 10 min
- Tools referenced: sec-filing-chunk-optimizer, financial-document-token-estimator, token-cost-optimizer

### Selection Bias in LLM Strategy Research
- URL: https://aifinhub.io/articles/selection-bias-in-llm-strategy-research/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: When an LLM proposes ten strategies and you pick the best, the apparent Sharpe is 1.5-2x the real edge. Deflated Sharpe and four discipline rules.
- Reading time: 9 min
- Tools referenced: backtest-overfitting-score, deflated-sharpe-ratio, walk-forward-validator

### Skill as Contract, Not Prompt: The Methodology Shift
- URL: https://aifinhub.io/articles/skill-as-contract-not-prompt/
- Archetype: Methodology · Opinion
- Published: 2026-05-21
- Description: Contract-form skills (typed I/O, runtime invariants, verification harness) survive drift and adversarial inputs that prompt-form skills cannot.
- Reading time: 12 min
- Tools referenced: structured-schema-validator-finance, prompt-injection-tester, hallucination-detector

### Sortino vs Sharpe: The Tail-Skew Tradeoff
- URL: https://aifinhub.io/articles/sortino-tradeoff-against-sharpe-tail-skew/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Same series, Sharpe 2.08 vs Sortino 2.90. The 39% gap is downside-only deviation discarding upside variance. When that read is honest and when it lies.
- Reading time: 7 min
- Tools referenced: sharpe-vs-sortino-calculator, returns-distribution-analyzer, backtest-overfitting-score

### Stat-Arb Capacity: Half-Life Sets the Ceiling
- URL: https://aifinhub.io/articles/stat-arb-capacity-pairs-half-life/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: A 7-day half-life pair returns $1B engine maxAum, $400M at 10bp slippage. Practical retail capacity sits orders of magnitude below. Half-life binds.
- Reading time: 7 min
- Tools referenced: statistical-arbitrage-capacity, cointegration-half-life-solver, execution-simulator

### Structural vs Fixed Chunking for SEC Filings
- URL: https://aifinhub.io/articles/structural-vs-fixed-chunking-decision/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: On a 14k-token earnings transcript, fixed chunking returns 8 chunks of 1,839 tokens; structural returns 30 of 565. Workload-bound, not cost-bound.
- Reading time: 7 min
- Tools referenced: sec-filing-chunk-optimizer, financial-document-token-estimator, token-cost-optimizer

### Synthetic Data: GARCH vs GBM for Backtesting
- URL: https://aifinhub.io/articles/synthetic-data-garch-vs-gbm-backtest/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: GBM Sharpe 1.91 on 504 days is the strategy null. GARCH paths add vol clustering — the regime that breaks vol-sensitive strategies. Run both.
- Reading time: 7 min
- Tools referenced: synthetic-market-data-generator, deflated-sharpe-ratio, walk-forward-validator

### Synthetic Data vs Bootstrap Resampling for Backtests
- URL: https://aifinhub.io/articles/synthetic-data-vs-bootstrap-resampling-backtests/
- Archetype: Comparison · Benchmark
- Published: 2026-05-21
- Description: GBM gives clean parametric paths; bootstrap preserves observed skew and vol clustering. For vol-sensitive strategies, run both, report the worst.
- Reading time: 7 min
- Tools referenced: synthetic-market-data-generator, walk-forward-validator, backtest-overfitting-score

### Token Cost Optimizer: Cache Amortization, Three Regimes
- URL: https://aifinhub.io/articles/token-cost-optimizer-cache-amortization/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine returns $46.94/month at 55% cache hit rate vs $74.65 at 0% — a 37% saving. The 13% break-even is approximate; real break-even sits closer to 8–10%.
- Reading time: 10 min
- Tools referenced: token-cost-optimizer, batch-vs-realtime-cost-calculator, agent-cost-envelope-calculator

### Trading System Blueprint: Alpaca + Claude Opus
- URL: https://aifinhub.io/articles/trading-system-blueprinter-databento-alpaca/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: A solo retail trading system in ~1,000 lines of Python, four launchd plists, one DuckDB. Seven decisions and three tests that catch 80% of failures.
- Reading time: 7 min
- Tools referenced: trading-system-blueprinter, broker-api-comparator, data-vendor-tco

### VaR Backtest: Kupiec vs Christoffersen on the Same Tape
- URL: https://aifinhub.io/articles/var-backtest-kupiec-vs-christoffersen-decision/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: Engine output on two tapes with 4 breaches each: Kupiec passes both (p=0.572); Christoffersen rejects clustering (p=0.011) and passes isolation.
- Reading time: 10 min
- Tools referenced: var-backtest-kupiec-christoffersen, returns-distribution-analyzer, risk-adjusted-returns

### Walk-Forward Window Sizing: A Decision Rule
- URL: https://aifinhub.io/articles/walk-forward-window-sizing-decision/
- Archetype: Pillar · Guide
- Published: 2026-05-21
- Description: On the canonical 50-bar tape the engine returns mean OOS Sharpe 0.653, efficiency 0.600 — but the four windows hide a regime flip the half-life rule fixes.
- Reading time: 11 min
- Tools referenced: walk-forward-validator, walk-forward-validation-visualizer, backtest-overfitting-score

### Walk-Forward Validation Pitfalls in LLM-Generated
- URL: https://aifinhub.io/articles/walk-forward-validation-pitfalls-llm-strategies/
- Archetype: Pillar · Guide
- Published: 2026-05-09
- Description: Eight pitfalls that quietly inflate walk-forward Sharpe in LLM-generated trading strategies — leakage, regime blindness, micro vs macro re-estimation.
- Reading time: 9 min
- Tools referenced: walk-forward-validator, backtest-overfitting-score, risk-adjusted-returns, walk-forward-validation-visualizer

### Retail PnL vs Backtest
- URL: https://aifinhub.io/articles/retail-pnl-vs-backtest-eight-mechanisms/
- Archetype: Pillar · Guide
- Published: 2026-05-09
- Description: The eleven-point gap between a 14% backtest and 3.2% live PnL, decomposed across eight mechanisms with dollar examples — slippage, latency, fees, fills.
- Reading time: 10 min
- Tools referenced: execution-simulator, walk-forward-validator, backtest-overfitting-score, drawdown-recovery-markov, pair-trading-tester

### Earnings Call Summarisation
- URL: https://aifinhub.io/articles/earnings-call-summarization-eight-llms-q2-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-05-09
- Description: Cost and architecture guide for earnings-call summarisation across eight production LLMs: verifiable 2026 vendor pricing and qualitative failure modes.
- Reading time: 9 min
- Tools referenced: model-selector-finance, hallucination-detector, token-cost-optimizer, earnings-call-summarization-cost

### MCP vs Custom HTTP: A Six-Scenario Decision
- URL: https://aifinhub.io/articles/mcp-vs-custom-http-when-each-wins/
- Archetype: Comparison · Benchmark
- Published: 2026-05-09
- Description: When does MCP beat a hand-rolled HTTP integration in agent finance stacks? Six concrete scenarios — multi-agent registry, auth scope, idempotent retries.
- Reading time: 9 min
- Tools referenced: finance-mcp-directory, trading-system-blueprinter

### Deflated Sharpe Ratio
- URL: https://aifinhub.io/articles/deflated-sharpe-derivation-worked-example/
- Archetype: Pillar · Guide
- Published: 2026-05-09
- Description: Bailey-López de Prado (2014) deflated Sharpe ratio, derived from extreme-value statistics, with a Monte Carlo confirmation and the full deflation table.
- Reading time: 11 min
- Tools referenced: backtest-overfitting-score, risk-adjusted-returns, walk-forward-validator, deflated-sharpe-ratio, sharpe-vs-sortino-calculator

### Why LLMs Fail Options Greeks
- URL: https://aifinhub.io/articles/why-gpt5-fails-options-greeks/
- Archetype: Methodology · Opinion
- Published: 2026-05-09
- Description: LLMs misfire on theta sign, vega-vs-gamma conflation, and ITM-vs-ATM gamma ranking. The three reproducible error categories, plus a verifier fix.
- Reading time: 10 min
- Tools referenced: options-greeks-explorer, options-payoff-builder, hallucination-detector

### Bond Yield Curve Parsing with Claude Haiku 4.5
- URL: https://aifinhub.io/articles/bond-yield-curve-parsing-claude-haiku/
- Archetype: Tutorial · Runnable
- Published: 2026-05-09
- Description: Extract US Treasury yield curves from auction announcements using Claude Haiku 4.5 — full prompt, deterministic verifier-in-the-loop pattern, evaluation.
- Reading time: 9 min
- Tools referenced: financial-document-token-estimator, hallucination-detector, token-cost-optimizer

### Risk Parity vs Kelly: When Each Sizing Framework
- URL: https://aifinhub.io/articles/risk-parity-vs-kelly-when-each-wins/
- Archetype: Comparison · Benchmark
- Published: 2026-05-09
- Description: Risk parity and Kelly solve different problems. Risk parity wins when correlations are stable and edge is noisy; Kelly wins when edge is concentrated.
- Reading time: 10 min
- Tools referenced: kelly-sizer, efficient-frontier-builder, correlation-matrix-visualizer, position-sizing-edge-variance

### Quant Interview: 50 Questions, LLM-Graded
- URL: https://aifinhub.io/articles/quant-interview-50-questions-llm-grading/
- Archetype: Pillar · Guide
- Published: 2026-05-09
- Description: Fifty quant interview questions — probability, statistics, derivatives, microstructure, regression — with answer keys and a Claude Sonnet 4.5 grading.
- Reading time: 12 min
- Tools referenced: hallucination-detector, model-selector-finance, quant-interview-question-generator

### Model Selection in Finance: Surviving Benchmarks
- URL: https://aifinhub.io/articles/model-selection-finance-survives-bench-cycles/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Model selection finance methodology: a five-axis rubric, quarterly rebench cadence, version-pinning, and shadow A/B that survive 3-6 month.
- Reading time: 13 min
- Tools referenced: model-selector-finance, prompt-regression-tester, agent-skill-tester, token-cost-optimizer, fallback-chain-simulator

### Backtest Overfitting in LLM Trading Strategies
- URL: https://aifinhub.io/articles/backtest-overfitting-llm-strategies-pbo-explained/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: The Probability of Backtest Overfitting, applied to LLM-augmented research. Why LLM strategies inflate PBO, how to compute it, and the three-gate.
- Reading time: 13 min
- Tools referenced: backtest-overfitting-score, walk-forward-validator, calibration-dojo, deflated-sharpe-ratio, walk-forward-validation-visualizer

### Caching Strategies for Production LLM Pipelines
- URL: https://aifinhub.io/articles/caching-strategies-llm-pipelines-2026/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Three caching layers for production LLM pipelines: provider-side prompt caching, application response cache, semantic similarity cache. Decision matrix +.
- Reading time: 11 min
- Tools referenced: token-cost-optimizer, agent-cost-envelope-calculator, data-vendor-tco

### Hallucination Detection at Scale
- URL: https://aifinhub.io/articles/hallucination-detection-at-scale-production/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Production-grade LLM hallucination detection in four layers: source grounding, self-consistency, deterministic verification, and adversarial probes.
- Reading time: 12 min
- Tools referenced: hallucination-detector, agent-skill-tester, prompt-regression-tester, price-blind-auditor

### MCP Servers for Financial Data
- URL: https://aifinhub.io/articles/mcp-servers-financial-data-security-graded/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: A five-grade A-E rubric for finance MCP servers across auth, egress, audit, rotation, and vendor posture. 12-server walkthrough plus anti-patterns.
- Reading time: 13 min
- Tools referenced: finance-mcp-directory, data-vendor-tco, structured-schema-validator-finance

### Production LLM Latency Budgets
- URL: https://aifinhub.io/articles/production-llm-latency-budgets-trading/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Trading apps with LLM-augmented research need explicit latency budgets per call. The P50/P95/P99 math, queue-theory bounds, and architecture patterns.
- Reading time: 11 min
- Tools referenced: agent-cost-envelope-calculator, execution-simulator

### Token-Cost Optimization
- URL: https://aifinhub.io/articles/token-cost-prompt-cache-vs-distill-vs-rag/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Three token-cost reduction strategies. Decision rules for when each pays back, and the math when they compound.
- Reading time: 11 min
- Tools referenced: token-cost-optimizer, agent-cost-envelope-calculator

### Compliance Audit Trails for LLM-Driven Trade
- URL: https://aifinhub.io/articles/compliance-audit-trails-llm-trades/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Schema, append-only log design, and reproducibility patterns for SEC/FINRA-compliant LLM trade audit trails.
- Reading time: 12 min
- Tools referenced: hallucination-detector, prompt-regression-tester, ftc-vs-nlt-regulatory-cost

### Vendor Lock-In Risk: How to Architect Cross-Provider
- URL: https://aifinhub.io/articles/vendor-lock-in-cross-provider-fallback/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Anthropic, OpenAI, and Google can all break or price-jump in one quarter. The fallback-chain architecture that survives a single-vendor outage.
- Reading time: 11 min
- Tools referenced: model-selector-finance, fallback-chain-simulator

### RAG vs Fine-Tuning: A Cost Model
- URL: https://aifinhub.io/articles/rag-cost-model-vs-fine-tuning/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: RAG looks cheaper at low query volume. Above 100k queries/month with stable knowledge, fine-tuning wins. The break-even math.
- Reading time: 11 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer

### Prompt Version Control
- URL: https://aifinhub.io/articles/prompt-version-control-git-workflows/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Prompts are code. Version them, diff them, regression-test them. Three workflow patterns that survive team scaling.
- Reading time: 10 min
- Tools referenced: prompt-regression-tester, agent-skill-tester

### MCP Server Latency: The Hidden Cost of Tool-Call
- URL: https://aifinhub.io/articles/mcp-server-latency-tool-call-roundtrips/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Each MCP tool call adds latency. For multi-step agents, the total roundtrip cost dominates. Architecture patterns to amortize it.
- Reading time: 10 min
- Tools referenced: finance-mcp-directory, agent-skill-tester

### Cost-Per-Validated-Trade
- URL: https://aifinhub.io/articles/cost-per-validated-trade-framework/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Tokens spent doesn't equal value. The cost-per-validated-trade metric and how to instrument it.
- Reading time: 11 min
- Tools referenced: token-cost-optimizer, calibration-dojo, kelly-sizer

### Calibration Drift: Why Your LLM's Confidence Score
- URL: https://aifinhub.io/articles/calibration-drift-llm-confidence-scores/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: LLM-reported confidence calibration drifts as the model is updated. Detection patterns and re-calibration math.
- Reading time: 11 min
- Tools referenced: calibration-dojo, prompt-regression-tester

### Temperature, Top-P, and Top-K
- URL: https://aifinhub.io/articles/temperature-top-p-top-k-production-cost/
- Archetype: Pillar · Guide
- Published: 2026-05-07
- Description: Sampling parameters affect both quality and cost. The decision rules for each parameter, with worked examples on production cost impact.
- Reading time: 10 min
- Tools referenced: token-cost-optimizer, agent-skill-tester

### Reading Financial Filings With LLMs: 2026 Playbook
- URL: https://aifinhub.io/articles/reading-financial-filings-with-llms-2026/
- Archetype: Pillar · Guide
- Published: 2026-04-23
- Description: A map of eight filing tasks — extraction, summarization, peer comparison, Q&A, classification, sentiment, forecasting input, compliance — with model.
- Reading time: 14 min
- Tools referenced: financial-document-token-estimator, sec-filing-chunk-optimizer, structured-schema-validator-finance, hallucination-detector, token-cost-optimizer

### Fine-Tuning vs RAG vs Long-Context for Filings
- URL: https://aifinhub.io/articles/finetune-vs-rag-vs-longcontext-filings/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: Decision matrix for finance LLMs: when RAG wins, when long-context wins, and when fine-tuning makes sense. Cost math from published 2026-04 vendor rates.
- Reading time: 12 min
- Tools referenced: financial-document-token-estimator, sec-filing-chunk-optimizer, token-cost-optimizer

### Prompt Caching Economics for Finance
- URL: https://aifinhub.io/articles/prompt-caching-economics-finance/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: How Anthropic, OpenAI, and Gemini prompt caching works on finance workloads — 5-minute TTL, hit-rate patterns, and 50-90% input savings at the right design.
- Reading time: 11 min
- Tools referenced: financial-document-token-estimator, token-cost-optimizer, batch-vs-realtime-cost-calculator

### Numeric Precision in LLM Filing Extraction
- URL: https://aifinhub.io/articles/numeric-precision-llm-filings/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Six precision traps — units, currency, GAAP vs non-GAAP, diluted vs basic shares, restatements, rounding — and the structured-output pattern that fixes them.
- Reading time: 11 min
- Tools referenced: structured-schema-validator-finance, hallucination-detector, agent-skill-tester

### Prompt Patterns for Earnings Calls
- URL: https://aifinhub.io/articles/prompt-patterns-earnings-calls/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Five copy-paste patterns — speaker attribution, hedged-guidance confidence, multi-quarter delta, risk aggregator, forward-outlook separator.
- Reading time: 12 min
- Tools referenced: agent-skill-tester, prompt-regression-tester, structured-schema-validator-finance, earnings-call-summarization-cost

### Observability Patterns for LLM Trading Agents
- URL: https://aifinhub.io/articles/observability-llm-trading-agents/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Three patterns that stop silent failure: trace-ID propagation, structured log schema with per-step cost and confidence, and a deterministic replay harness.
- Reading time: 11 min
- Tools referenced: trading-system-blueprinter, agent-cost-envelope-calculator, token-cost-optimizer

### MCP vs Function Calling for Finance Agents
- URL: https://aifinhub.io/articles/mcp-vs-function-calling-finance/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: Where MCP wins, where function calling wins, and why the right answer is almost always a hybrid — data layer on MCP, decision code on function calling.
- Reading time: 10 min
- Tools referenced: finance-mcp-directory, agent-skill-tester, trading-system-blueprinter

### Rate Limit Design for LLM Research Loops
- URL: https://aifinhub.io/articles/rate-limit-design-llm-research/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Three primitives that turn bursty finance workloads into stable loops: per-provider token bucket, cross-provider fallback chain, and graceful degradation.
- Reading time: 10 min
- Tools referenced: fallback-chain-simulator, token-cost-optimizer, trading-system-blueprinter

### Bounded-Cost Agentic Research
- URL: https://aifinhub.io/articles/bounded-cost-agentic-research/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: Three gates stop runaway agent loops: hard token budget, step-count cap, and a cost-convergence check that halts when belief stops moving.
- Reading time: 10 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer, trading-system-blueprinter

### Prompt Injection Defenses for Finance Agents
- URL: https://aifinhub.io/articles/prompt-injection-defenses-finance/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: Five stacked defenses: input fencing, output validation, tool allow-list, bounded-cost circuit, dual-model cross-check. No single defense is sufficient.
- Reading time: 11 min
- Tools referenced: prompt-injection-tester, hallucination-detector, agent-skill-tester

### Agent Memory Patterns for Finance Research
- URL: https://aifinhub.io/articles/agent-memory-patterns-finance/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Three memory tiers for finance agents — working, episodic, long-term lesson library — with retention policies and runnable Python for each.
- Reading time: 11 min
- Tools referenced: agent-skill-tester, agent-cost-envelope-calculator, trading-system-blueprinter

### Model Selection Framework for Finance Tasks
- URL: https://aifinhub.io/articles/model-selection-framework-finance/
- Archetype: Comparison · Benchmark
- Published: 2026-04-23
- Description: A task × latency × cost × context decision tree for finance LLM workloads. Ten concrete scenarios mapped to tier bands. Grounded in published pricing, not.
- Reading time: 12 min
- Tools referenced: model-selector-finance, token-cost-optimizer, financial-document-token-estimator, var-backtest-kupiec-christoffersen, deflated-sharpe-ratio

### Batch API Economics for Finance Loops
- URL: https://aifinhub.io/articles/batch-api-economics-finance/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: When Anthropic Message Batches or OpenAI Batch cut cost by half on finance workloads — and the soft-deadline rule for when batch is not a valid choice.
- Reading time: 11 min
- Tools referenced: batch-vs-realtime-cost-calculator, financial-document-token-estimator, token-cost-optimizer

### Thinking Tokens for Finance Tasks
- URL: https://aifinhub.io/articles/thinking-tokens-finance-tasks/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: When extended-thinking and reasoning-effort modes earn their 3-10x cost tax on finance workloads — and when they are a silent drain on the budget.
- Reading time: 11 min
- Tools referenced: model-selector-finance, token-cost-optimizer, financial-document-token-estimator

### Inference Cost Attribution per Idea and Trade
- URL: https://aifinhub.io/articles/inference-cost-attribution-trade/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Append-only cost-event schema plus two canonical SQL queries — cost per idea, cost per validated trade — with cache-write amortization built in.
- Reading time: 11 min
- Tools referenced: agent-cost-envelope-calculator, token-cost-optimizer, batch-vs-realtime-cost-calculator

### Context Hygiene for Multi-Step Research
- URL: https://aifinhub.io/articles/context-hygiene-multi-step-research/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Three-tier layered summary — leaf documents, intermediate briefs, working memory — with per-tier retention rules that keep long research loops cheap and sharp.
- Reading time: 10 min
- Tools referenced: financial-document-token-estimator, token-cost-optimizer, agent-skill-tester

### Evaluation Harness for Finance LLM Tasks
- URL: https://aifinhub.io/articles/eval-harness-finance-llm/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Why public benchmarks are a signal not a decision, how to source ground truth from EDGAR, and a runnable eval-harness skeleton with bootstrap confidence.
- Reading time: 12 min
- Tools referenced: agent-skill-tester, prompt-regression-tester, hallucination-detector

### Bayesian Updating for LLM-Assisted Forecasts
- URL: https://aifinhub.io/articles/bayesian-updating-llm-forecasts/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Turn LLM probability outputs into calibrated posteriors — Beta-Binomial for binary forecasts, Normal-Inverse-Gamma for continuous — with runnable Python.
- Reading time: 11 min
- Tools referenced: calibration-dojo, kelly-sizer, backtest-overfitting-score

### Brier Scores and Log Loss for Forecasters
- URL: https://aifinhub.io/articles/brier-scores-log-loss-forecasters/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Two proper scoring rules for probabilistic forecasts, why Brier decomposes into reliability plus resolution, and why log loss punishes overconfident wrongness.
- Reading time: 10 min
- Tools referenced: forecast-scoring-sandbox, calibration-dojo, kelly-sizer

### Research Diary Schema: Auditable LLM Research
- URL: https://aifinhub.io/articles/research-diary-schema-auditable/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: A 12-field append-only schema that captures every idea — including rejected ones — to unlock calibration, proper scoring, and post-hoc overfitting analysis.
- Reading time: 10 min
- Tools referenced: calibration-dojo, backtest-overfitting-score, forecast-scoring-sandbox

### Multi-Timeframe Signal Integration With LLMs
- URL: https://aifinhub.io/articles/multi-timeframe-signal-integration-llms/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: LLMs belong on weekly fundamentals, not intraday microstructure. A two-layer architecture: weekly LLM thesis plus rule-based intraday invalidation gates.
- Reading time: 11 min
- Tools referenced: correlation-matrix-visualizer, kelly-sizer, token-cost-optimizer, cointegration-half-life-solver, pair-trading-tester

### News Feed Integration for Finance Agents
- URL: https://aifinhub.io/articles/news-feed-integration-finance-agents/
- Archetype: Tutorial · Runnable
- Published: 2026-04-23
- Description: Four patterns — source vetting, injection sanitization, timestamp discipline, dedup across reporters — make news safe for an LLM finance agent. Runnable.
- Reading time: 11 min
- Tools referenced: prompt-injection-tester, hallucination-detector, agent-skill-tester

### After-Hours, 24-7, and Pre-Market Asymmetries
- URL: https://aifinhub.io/articles/after-hours-247-premarket-asymmetries/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: Three boundaries where LLM research built on equity's 9:30–16:00 clock breaks — earnings after close, 24-7 crypto, pre-market Asia/Europe action. Decision rule.
- Reading time: 10 min
- Tools referenced: execution-simulator, token-cost-optimizer, returns-distribution-analyzer, kalshi-poly-arb

### Postmortem Template for LLM Trading Systems
- URL: https://aifinhub.io/articles/postmortem-template-llm-trading-systems/
- Archetype: Methodology · Opinion
- Published: 2026-04-23
- Description: A blameless, append-only postmortem template plus a 20-mode failure checklist — price-blind leaks to cache poisoning — keyed to the trace-ID log.
- Reading time: 10 min
- Tools referenced: price-blind-auditor, hallucination-detector, prompt-injection-tester

### Walk-Forward Validation: A Cookbook
- URL: https://aifinhub.io/articles/walk-forward-validation-cookbook/
- Archetype: Tutorial · Runnable
- Published: 2026-04-22
- Description: Walk-forward is the cheapest honest backtest you can run. Anchored vs rolling windows, the four parameters that matter, and a 60-line Python template.
- Reading time: 11 min
- Tools referenced: walk-forward-validator, backtest-overfitting-score, risk-adjusted-returns, walk-forward-validation-visualizer

### Prompt Injection Attack Catalog for Finance Agents
- URL: https://aifinhub.io/articles/prompt-injection-attack-catalog-finance/
- Archetype: Methodology · Opinion
- Published: 2026-04-22
- Description: Prompt injection attacks on finance agents — indirect injection via news feeds, tool-result poisoning, prompt exfiltration, unit confusion — plus defenses.
- Reading time: 10 min
- Tools referenced: prompt-injection-tester, hallucination-detector, price-blind-auditor

### Backtest to Paper to Live: Deployment Playbook
- URL: https://aifinhub.io/articles/backtest-to-paper-to-live-playbook/
- Archetype: Tutorial · Runnable
- Published: 2026-04-22
- Description: Backtest to paper to live — the gates that separate each stage, the metrics that trigger rollback, and the kill-switch you should already have.
- Reading time: 12 min
- Tools referenced: trading-system-blueprinter, execution-simulator, backtest-overfitting-score

### The $0/Month Trading Stack in 2026
- URL: https://aifinhub.io/articles/zero-dollar-trading-stack/
- Archetype: Methodology · Opinion
- Published: 2026-04-22
- Description: Zero-cost solo trading stack: launchd + free market data tiers + local LLMs on cheap paths + BYO API keys — plus where paid tiers become unavoidable.
- Reading time: 10 min
- Tools referenced: data-vendor-tco, token-cost-optimizer, trading-system-blueprinter

### Real-Time vs End-of-Day Trading Systems
- URL: https://aifinhub.io/articles/real-time-vs-end-of-day-systems/
- Archetype: Methodology · Opinion
- Published: 2026-04-22
- Description: Real-time vs end-of-day trading systems — the decision rule, the 20-50x cost delta, and the four signal types where real-time is genuinely load-bearing.
- Reading time: 9 min
- Tools referenced: data-vendor-tco, execution-simulator

### Rate-Limited, Resumable Market-Data Ingestion
- URL: https://aifinhub.io/articles/rate-limited-resumable-market-data-ingestion/
- Archetype: Tutorial · Runnable
- Published: 2026-04-22
- Description: Four primitives that turn a weekend ingestion script into a six-month loop: token-bucket limits, resumable checkpoints, idempotent writes, DLQs.
- Reading time: 11 min
- Tools referenced: data-vendor-tco, trading-system-blueprinter

### Synthetic Market Data for Backtests: Beyond GBM
- URL: https://aifinhub.io/articles/synthetic-market-data-for-backtests/
- Archetype: Tutorial · Runnable
- Published: 2026-04-22
- Description: Synthetic market data beyond GBM — when GARCH(1,1), regime-switching, or copula-linked pairs are the right next step. Trade-offs plus a Python template.
- Reading time: 10 min
- Tools referenced: synthetic-market-data-generator, backtest-overfitting-score, walk-forward-validator

### Execution Simulation: Slippage and Impact
- URL: https://aifinhub.io/articles/execution-simulation-slippage-impact/
- Archetype: Methodology · Opinion
- Published: 2026-04-22
- Description: The math of market impact — why it scales as the square root of trade size, when linear impact dominates, and the fix that keeps backtests honest.
- Reading time: 11 min
- Tools referenced: execution-simulator, order-book-replay, risk-adjusted-returns, pair-trading-tester

### Choosing a Broker API in 2026
- URL: https://aifinhub.io/articles/choosing-a-broker-api-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-04-22
- Description: Choosing a broker API 2026 — Alpaca vs IBKR vs Tradier vs Schwab vs Robinhood on the axes that bite: auth, order types, rate limits, and fees.
- Reading time: 10 min
- Tools referenced: broker-api-comparator, finance-mcp-directory, data-vendor-tco

### Options Greeks for LLM-Driven Trading
- URL: https://aifinhub.io/articles/options-greeks-for-llm-driven-trading/
- Archetype: Tutorial · Runnable
- Published: 2026-04-22
- Description: Options Greeks for LLM-driven trading: delta, gamma, theta, vega, rho — what each costs, three rules, plus a prompt template for multi-leg positions.
- Reading time: 10 min
- Tools referenced: options-greeks-explorer, options-payoff-builder, agent-skill-tester

### The Sharpe Ratio Trap
- URL: https://aifinhub.io/articles/sharpe-ratio-trap/
- Archetype: Methodology · Opinion
- Published: 2026-04-22
- Description: Sharpe ignores tail risk, assumes Gaussian returns, and is trivially gameable. Four metrics to report alongside it: Sortino, Calmar, tail, deflated Sharpe.
- Reading time: 8 min
- Tools referenced: risk-adjusted-returns, returns-distribution-analyzer, backtest-overfitting-score, sharpe-vs-sortino-calculator, deflated-sharpe-ratio

### The 2026 Engineer's Guide to AI in Markets
- URL: https://aifinhub.io/articles/the-2026-engineers-guide-to-ai-in-markets/
- Archetype: Pillar · Guide
- Published: 2026-04-20
- Description: An engineer's map of where LLMs, MCP servers, and market-data APIs fit into a 2026 trading stack — and where they still break. Direct, no hype, no grift.
- Reading time: 10 min
- Tools referenced: data-vendor-tco, finance-mcp-directory, token-cost-optimizer, backtest-overfitting-score, kelly-sizer

### Market Data APIs Compared: Databento vs Polygon 2026
- URL: https://aifinhub.io/articles/market-data-apis-compared-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-04-20
- Description: Market data APIs compared: six retail providers on pricing, tier coverage, real-time access, options and futures coverage, and who wins for each profile.
- Reading time: 9 min
- Tools referenced: data-vendor-tco, finance-mcp-directory

### Broker APIs Compared: Alpaca vs IBKR vs Tradier 2026
- URL: https://aifinhub.io/articles/broker-apis-compared-2026/
- Archetype: Comparison · Benchmark
- Published: 2026-04-20
- Description: Broker APIs for retail AI trading 2026: Alpaca for solo ops (official MCP), IBKR for multi-asset depth, Tradier for options. Head-to-head + MCP angle.
- Reading time: 8 min
- Tools referenced: finance-mcp-directory, data-vendor-tco, trading-system-blueprinter

### Finance MCP Servers: The Security Baseline
- URL: https://aifinhub.io/articles/finance-mcp-security-baseline/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: An opinionated rubric for grading 2026 finance MCP servers on scope, auth, idempotency, transport, and schema — plus the failure modes that kill agents.
- Reading time: 11 min
- Tools referenced: finance-mcp-directory, trading-system-blueprinter

### The Price-Blind LLM Research Harness
- URL: https://aifinhub.io/articles/price-blind-llm-research-harness/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: Price-blind LLM research — most harnesses leak the current price and the model confabulates. The architectural fix and a 30-line Python scaffold.
- Reading time: 8 min
- Tools referenced: prompt-regression-tester, hallucination-detector, calibration-dojo

### The 8-Step LLM Research Prompt Template
- URL: https://aifinhub.io/articles/8-step-llm-research-prompt-template/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: Free-form prompts yield uncalibrated LLM output. An 8-step template makes research reproducible and better-calibrated across model versions.
- Reading time: 9 min
- Tools referenced: prompt-regression-tester, agent-skill-tester

### LLM Prompt Patterns for 10-K and 8-K Extraction
- URL: https://aifinhub.io/articles/llm-prompt-patterns-10k-extraction/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: Three structured patterns for auditable 10-K extractions: field-by-field JSON, citation-required verbatim quotes, and contradiction-triangle cross-check.
- Reading time: 9 min
- Tools referenced: hallucination-detector, agent-skill-tester, token-cost-optimizer

### Did You Overfit? PBO and Deflated Sharpe
- URL: https://aifinhub.io/articles/did-you-overfit-pbo-deflated-sharpe/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: A practical tutorial on the two best-documented tests for backtest overfitting — PBO via CSCV and the Deflated Sharpe Ratio. Runnable Python + tool.
- Reading time: 12 min
- Tools referenced: backtest-overfitting-score, kelly-sizer, deflated-sharpe-ratio, walk-forward-validation-visualizer

### Signal Orthogonality: Why Ensembles Become One Bet
- URL: https://aifinhub.io/articles/signal-orthogonality-ensembles/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: A 10-signal ensemble with pairwise correlation 0.8 is effectively a 1.5-signal ensemble. The math, a two-minute diagnostic, and three axes that work.
- Reading time: 7 min
- Tools referenced: backtest-overfitting-score, kelly-sizer, cointegration-half-life-solver, statistical-arbitrage-capacity

### Conviction-Scaled Kelly Bet Sizing
- URL: https://aifinhub.io/articles/conviction-scaled-kelly/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: Full Kelly is brutally unforgiving of over-estimation. Quarter-Kelly with a conviction-tier mapping and a per-trade cap is the defensible default.
- Reading time: 8 min
- Tools referenced: kelly-sizer, backtest-overfitting-score, calibration-dojo, position-sizing-edge-variance

### Calibrating LLM Forecasts with Isotonic Regression
- URL: https://aifinhub.io/articles/isotonic-calibration-llm-forecasts/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: LLM probabilities are systematically miscalibrated. Isotonic regression via PAV is the cheapest robust fix: 40 lines of Python, no distributional priors.
- Reading time: 10 min
- Tools referenced: calibration-dojo, kelly-sizer, backtest-overfitting-score

### Heartbeats, Watchdogs, Circuit Breakers for Trading
- URL: https://aifinhub.io/articles/heartbeats-watchdogs-circuit-breakers/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: Silent failure is the worst failure mode. Three patterns prevent it — heartbeat, watchdog, circuit breaker — in under 100 lines of Python on launchd.
- Reading time: 9 min
- Tools referenced: trading-system-blueprinter, finance-mcp-directory, token-cost-optimizer

### The Token-Cost Reality of LLM Trading Research
- URL: https://aifinhub.io/articles/token-cost-reality-llm-trading-research/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: What LLM trading research costs per idea and per validated trade across Claude, GPT-5, and Gemini 2.5. Pricing, caching, model-mix under $200/month.
- Reading time: 8 min
- Tools referenced: token-cost-optimizer, prompt-regression-tester

### Building a Production Claude Agent for Finance
- URL: https://aifinhub.io/articles/production-claude-agent-for-finance/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: Production Claude agent for finance: price-blind research, idempotent execution, heartbeat + watchdog + circuit breaker, under $225/month at small scale.
- Reading time: 14 min
- Tools referenced: trading-system-blueprinter, token-cost-optimizer, kelly-sizer, finance-mcp-directory, walk-forward-validator

### The BaFin + EU Guide for Retail AI Traders (2026)
- URL: https://aifinhub.io/articles/bafin-eu-guide-retail-ai-traders/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: BaFin and EU rules for retail AI trading, publishing finance content, and automated strategies. Education-safe phrasing and the minimum compliance stack.
- Reading time: 12 min
- Tools referenced: ftc-vs-nlt-regulatory-cost

### The 5 Failure Modes of LLM Trading Agents (2026)
- URL: https://aifinhub.io/articles/5-failure-modes-llm-trading-agents/
- Archetype: Methodology · Opinion
- Published: 2026-04-20
- Description: The 5 recurring failure modes in retail LLM trading agents: price-blind leaks, numeric fabrication, prompt drift, token runaway, audit amnesia.
- Reading time: 8 min
- Tools referenced: price-blind-auditor, hallucination-detector, prompt-regression-tester, token-cost-optimizer, trading-system-blueprinter, llm-finance-error-taxonomy

### How to Read a Backtest Report: 2026 Cheat Sheet
- URL: https://aifinhub.io/articles/how-to-read-a-backtest-report/
- Archetype: Tutorial · Runnable
- Published: 2026-04-20
- Description: Five questions a backtest report must answer — edge real, persistent, cheap to trade, bearable, explainable — with the statistics that verify each.
- Reading time: 9 min
- Tools referenced: backtest-overfitting-score, walk-forward-validator, risk-adjusted-returns, returns-distribution-analyzer, correlation-matrix-visualizer, drawdown-recovery-markov, walk-forward-validation-visualizer

## Resources (244 total)

### Guides (33)
- How to Audit a Research Prompt for Look-Ahead Leakage: https://aifinhub.io/guides/how-to-audit-a-research-prompt-for-look-ahead-leakage/
  Description: Audit an LLM research prompt for look-ahead leakage: scan for outcome-revealing prices, directional words, and future facts the model could cheat with.
  Updated: 2026-05-26
- How to Avoid Backtest Overfitting: https://aifinhub.io/guides/how-to-avoid-backtest-overfitting/
  Description: Avoid backtest overfitting with a practical workflow: limit trials, hold out data, measure the probability of overfitting, prefer robust rules.
  Updated: 2026-05-26
- How to Backtest a Value-at-Risk Model: https://aifinhub.io/guides/how-to-backtest-a-value-at-risk-model/
  Description: Backtest a value-at-risk model: count breaches, run the Kupiec frequency test and the Christoffersen independence test, and read clustered breaches.
  Updated: 2026-05-26
- How to Backtest with Realistic Slippage: https://aifinhub.io/guides/how-to-backtest-with-realistic-slippage/
  Description: Backtest with realistic slippage: model the spread, temporary and permanent market impact, latency, and partial fills so paper returns survive live.
  Updated: 2026-05-26
- How to Build a RAG Pipeline Over SEC Filings: https://aifinhub.io/guides/how-to-build-a-rag-pipeline-over-sec-filings/
  Description: Build a RAG pipeline over SEC filings: ingest and chunk 10-Ks, embed and retrieve passages, ground answers with citations, and verify extracted numbers.
  Updated: 2026-05-26
- How to Build a Regression Suite for a Finance Prompt: https://aifinhub.io/guides/how-to-build-a-regression-suite-for-a-finance-prompt/
  Description: Build a regression suite for a finance prompt: collect representative and adversarial cases, define expected outputs, and run it on every change.
  Updated: 2026-05-26
- How to Build an Efficient Frontier: https://aifinhub.io/guides/how-to-build-an-efficient-frontier/
  Description: Build an efficient frontier: estimate expected returns and the covariance matrix, solve minimum-variance portfolios, and handle estimation error.
  Updated: 2026-05-26
- How to Calibrate Probability Forecasts: https://aifinhub.io/guides/how-to-calibrate-probability-forecasts/
  Description: Calibrate probability forecasts: score with Brier and log loss, read a reliability diagram, apply Platt or isotonic recalibration, confirm the fix.
  Updated: 2026-05-26
- How to Choose a Market Data Vendor: https://aifinhub.io/guides/how-to-choose-a-market-data-vendor/
  Description: Choose a market data vendor by matching coverage, resolution, and history to your strategy, then comparing total cost of ownership across vendors.
  Updated: 2026-05-26
- How to Choose a Risk-Adjusted Return Metric: https://aifinhub.io/guides/how-to-choose-a-risk-adjusted-return-metric/
  Description: Choose a risk-adjusted return metric by matching what it penalizes to the risk you care about: Sharpe, Sortino, Calmar, Omega, information ratio.
  Updated: 2026-05-26
- How to Choose Between RAG and Fine-Tuning for Filings: https://aifinhub.io/guides/how-to-choose-between-rag-and-fine-tuning-for-filings/
  Description: Choose between RAG and fine-tuning for filings: match the method to whether the task needs fresh knowledge or a fixed format, then weigh the cost.
  Updated: 2026-05-26
- How to Choose Between Sharpe and Sortino: https://aifinhub.io/guides/how-to-choose-between-sharpe-and-sortino/
  Description: Choose between Sharpe and Sortino by matching the metric to your returns: Sharpe for symmetric returns, Sortino when downside is the concern.
  Updated: 2026-05-26
- How to Compute a Deflated Sharpe Ratio: https://aifinhub.io/guides/how-to-compute-a-deflated-sharpe-ratio/
  Description: Compute a deflated Sharpe ratio step by step: gather the inputs, count trials, adjust for skew and kurtosis, and read the probability the edge is real.
  Updated: 2026-05-26
- How to Cut LLM Token Cost in a Finance Agent: https://aifinhub.io/guides/how-to-cut-llm-token-cost-in-a-finance-agent/
  Description: Cut LLM token cost in a finance agent: right-size the model, cache the stable prefix, trim context, batch deferrable work, measure cost per decision.
  Updated: 2026-05-26
- How to Decide Between Batch and Real-Time LLM Calls: https://aifinhub.io/guides/how-to-decide-between-batch-and-real-time-llm-calls/
  Description: Decide between batch and real-time LLM calls by deadline: route latency-tolerant jobs to batch for the discount, keep waiting-on work real-time.
  Updated: 2026-05-26
- How to Defend a Finance LLM Against Prompt Injection: https://aifinhub.io/guides/how-to-defend-a-finance-llm-against-prompt-injection/
  Description: Defend a finance LLM against prompt injection: treat retrieved content as untrusted, separate instructions from data, restrict tools, test attacks.
  Updated: 2026-05-26
- How to Deploy an LLM in a Finance Pipeline: https://aifinhub.io/guides/how-to-deploy-an-llm-in-a-finance-pipeline/
  Description: A practical guide to putting a large language model into a finance workflow safely: scoping the task, grounding answers, guarding inputs, and verifying every number.
  Updated: 2026-05-26
- How to Design a Fallback Chain for LLM Providers: https://aifinhub.io/guides/how-to-design-a-fallback-chain-for-llm-providers/
  Description: Design a fallback chain for LLM providers: order models by quality and cost, set timeouts and retries, handle rate limits, and simulate failures first.
  Updated: 2026-05-26
- How to Detect Hallucinations in Finance LLM Output: https://aifinhub.io/guides/how-to-detect-hallucinations-in-finance-llm-output/
  Description: Detect hallucinations in finance LLM output: verify every number against the source, check citation faithfulness, and flag unsupported claims.
  Updated: 2026-05-26
- How to Estimate Drawdown Recovery Time: https://aifinhub.io/guides/how-to-estimate-drawdown-recovery-time/
  Description: Estimate drawdown recovery time from a strategy's return moments: run a Cornish-Fisher Monte Carlo, read the recovery percentiles, plan for the tail.
  Updated: 2026-05-26
- How to Estimate the Cost of an AI Research Agent: https://aifinhub.io/guides/how-to-estimate-the-cost-of-an-ai-research-agent/
  Description: Estimate the cost of an AI research agent: count tokens per step, multiply by tool calls and retries, scale to markets per day, and add a cost cap.
  Updated: 2026-05-26
- How to Evaluate an LLM for 10-K Extraction: https://aifinhub.io/guides/how-to-evaluate-an-llm-for-10-k-extraction/
  Description: Evaluate an LLM for 10-K extraction: build a labeled gold set, score field accuracy and faithfulness, test edge cases, weigh cost against quality.
  Updated: 2026-05-26
- How to Generate Synthetic Market Data for Testing: https://aifinhub.io/guides/how-to-generate-synthetic-market-data-for-testing/
  Description: Generate synthetic market data for testing: choose a process that captures fat tails and volatility clustering, then use it without overfitting.
  Updated: 2026-05-26
- How to Get Structured Output from a Finance LLM: https://aifinhub.io/guides/how-to-get-structured-output-from-a-finance-llm/
  Description: Get reliable structured output from a finance LLM: define a strict schema, constrain generation, validate every field, and verify the numbers.
  Updated: 2026-05-26
- How to Read Options Greeks: https://aifinhub.io/guides/how-to-read-options-greeks/
  Description: Read the options Greeks in plain terms: delta, gamma, theta, vega, and rho, what each measures, how they interact, and how to manage a position.
  Updated: 2026-05-26
- How to Run Walk-Forward Validation: https://aifinhub.io/guides/how-to-run-walk-forward-validation/
  Description: Run walk-forward validation: choose anchored or rolling windows, set fit and test lengths, re-optimize per window, and aggregate out-of-sample results.
  Updated: 2026-05-26
- How to Select an LLM for a Finance Task: https://aifinhub.io/guides/how-to-select-an-llm-for-a-finance-task/
  Description: Select an LLM for a finance task by defining task, latency, cost, context, and quality constraints, then ranking on your own eval, not benchmarks.
  Updated: 2026-05-26
- How to Set Up Prompt Caching for Finance: https://aifinhub.io/guides/how-to-set-up-prompt-caching-for-finance/
  Description: Set up prompt caching for finance LLM workloads: identify the stable prefix, order the prompt for cache hits, manage the window, measure savings.
  Updated: 2026-05-26
- How to Size Positions with Kelly Under Uncertainty: https://aifinhub.io/guides/how-to-size-positions-with-kelly-under-uncertainty/
  Description: Size positions with the Kelly criterion when your edge is uncertain: estimate edge and variance, apply fractional Kelly, and stress-test the drawdown.
  Updated: 2026-05-26
- How to Summarize Earnings Calls with an LLM: https://aifinhub.io/guides/how-to-summarize-earnings-calls-with-an-llm/
  Description: Summarize earnings calls with an LLM reliably: scope the summary, ground it in the transcript with citations, verify figures, estimate the cost.
  Updated: 2026-05-26
- How to Test a Pair for Cointegration: https://aifinhub.io/guides/how-to-test-a-pair-for-cointegration/
  Description: Test a pair for cointegration with Engle-Granger: estimate the hedge ratio, run an ADF test on the residual, measure the half-life, validate it.
  Updated: 2026-05-26
- How to Test an Agent Skill for a Finance Task: https://aifinhub.io/guides/how-to-test-an-agent-skill-for-a-finance-task/
  Description: Test an agent skill for a finance task: define the skill, run representative and adversarial inputs, score extraction, and measure cost and latency.
  Updated: 2026-05-26
- How to Validate a Trading Strategy: https://aifinhub.io/guides/how-to-validate-a-trading-strategy/
  Description: A step-by-step process for validating a trading strategy without fooling yourself: out-of-sample testing, trial accounting, deflated Sharpe, and a VaR backtest.
  Updated: 2026-05-26

### Checklists (28)
- AI in Finance Audit Trail Checklist: https://aifinhub.io/checklists/ai-finance-compliance-audit-trail-checklist/
  Description: AI finance audit trail checklist: log inputs and outputs, version prompts and models, record sign-off, and retain reconstructable records.
  Updated: 2026-05-26
- Backtest Hygiene Checklist: https://aifinhub.io/checklists/backtest-hygiene-checklist/
  Description: Backtest hygiene checklist: point-in-time data, realistic costs, no look-ahead, aligned returns, and a reproducible run before you trust a number.
  Updated: 2026-05-26
- Broker API Integration Checklist: https://aifinhub.io/checklists/broker-api-integration-checklist/
  Description: Broker API integration checklist: verify auth and order types, handle rate limits and partial fills, reconcile positions, and add idempotency.
  Updated: 2026-05-26
- Earnings Call Summarization Pipeline Checklist: https://aifinhub.io/checklists/earnings-call-summarization-pipeline-checklist/
  Description: Earnings call summarization checklist: handle long transcripts, ground claims, verify guidance numbers, control cost, and audit the output.
  Updated: 2026-05-26
- Execution Cost Audit Checklist: https://aifinhub.io/checklists/execution-cost-audit-checklist/
  Description: Execution cost audit checklist: measure spread, impact, slippage, and fees per fill, benchmark against arrival, and confirm the edge survives.
  Updated: 2026-05-26
- Feature Leakage Audit Checklist: https://aifinhub.io/checklists/feature-leakage-audit-checklist/
  Description: Feature leakage audit checklist: hunt full-sample stats, overlapping labels, restated fundamentals, and target contamination before they fake an edge.
  Updated: 2026-05-26
- Finance Agent Fallback Resilience Checklist: https://aifinhub.io/checklists/finance-agent-fallback-resilience-checklist/
  Description: LLM fallback chain checklist: define a provider fallback, handle rate limits and timeouts, set degradation modes, and test the failure paths.
  Updated: 2026-05-26
- Forecast Calibration Review Checklist: https://aifinhub.io/checklists/forecast-calibration-review-checklist/
  Description: Forecast calibration checklist: score with Brier and log loss, read the reliability curve, separate calibration from discrimination, honestly.
  Updated: 2026-05-26
- Hallucination Guardrails for Finance LLMs: https://aifinhub.io/checklists/hallucination-guardrails-finance-checklist/
  Description: Hallucination guardrails checklist: ground answers, verify every number, check citation faithfulness, and gate any money-moving output.
  Updated: 2026-05-26
- LLM Cost Control Checklist: https://aifinhub.io/checklists/llm-cost-control-checklist/
  Description: LLM cost control checklist: right-size the model, cache and batch, cap the agent loop, and set spend alerts before the first surprise invoice.
  Updated: 2026-05-26
- LLM Finance Evaluation Design Checklist: https://aifinhub.io/checklists/llm-finance-eval-design-checklist/
  Description: LLM finance evaluation checklist: build a representative test set, include adversarial cases, choose scorable metrics, and avoid contamination.
  Updated: 2026-05-26
- LLM for Finance Deployment Checklist: https://aifinhub.io/checklists/llm-for-finance-deployment-checklist/
  Description: A pre-flight checklist for putting a large language model into a finance workflow: scoping, grounding, input security, numerical verification, and drift monitoring.
  Updated: 2026-05-26
- LLM Model Risk Management Checklist: https://aifinhub.io/checklists/llm-model-risk-management-checklist/
  Description: LLM model risk management checklist: inventory the model, document assumptions, validate outputs independently, monitor drift, and govern it.
  Updated: 2026-05-26
- LLM Output Schema Validation Checklist: https://aifinhub.io/checklists/llm-output-schema-validation-checklist/
  Description: LLM output validation checklist: define a strict schema, validate types and ranges, sanity-check values, and fail safe on nonconforming output.
  Updated: 2026-05-26
- Market Data Vendor Selection Checklist: https://aifinhub.io/checklists/market-data-vendor-selection-checklist/
  Description: Market data vendor checklist: match coverage and resolution, verify point-in-time history, compute true total cost, and check licensing first.
  Updated: 2026-05-26
- Options Strategy Review Checklist: https://aifinhub.io/checklists/options-strategy-review-checklist/
  Description: Options strategy checklist: verify the payoff and break-evens, map the Greeks, bound max loss, and stress vol and time decay before the trade.
  Updated: 2026-05-26
- Overfitting Red-Flags Checklist: https://aifinhub.io/checklists/overfitting-red-flags-checklist/
  Description: Overfitting red-flags checklist: spot high trial counts, fragile parameters, suspiciously smooth equity, and in-sample-only edge before you deploy.
  Updated: 2026-05-26
- Pairs Trading Validation Checklist: https://aifinhub.io/checklists/pairs-trading-validation-checklist/
  Description: Pairs trading checklist: test for genuine cointegration, measure the half-life, guard against spurious pairs, and stress the spread first.
  Updated: 2026-05-26
- Paper-to-Live Transition Checklist: https://aifinhub.io/checklists/paper-to-live-transition-checklist/
  Description: Paper-to-live transition checklist: reconcile fills against real costs, start at minimum size, set kill switches, and verify live matches backtest.
  Updated: 2026-05-26
- Portfolio Construction Review Checklist: https://aifinhub.io/checklists/portfolio-construction-review-checklist/
  Description: Portfolio construction checklist: vet correlation inputs, control optimizer error-maximization, set constraints, and verify the frontier first.
  Updated: 2026-05-26
- Position Sizing Review Checklist: https://aifinhub.io/checklists/position-sizing-review-checklist/
  Description: Position sizing checklist: size from edge and its uncertainty, apply fractional Kelly, cap correlated exposure, and stress the drawdown first.
  Updated: 2026-05-26
- Pre-Deployment Trading Strategy Review: https://aifinhub.io/checklists/pre-deployment-trading-strategy-review-checklist/
  Description: Trading strategy review checklist: a final sign-off on edge evidence, risk limits, capacity, operations, and an exit plan before capital goes live.
  Updated: 2026-05-26
- Prompt Design for Financial Extraction: https://aifinhub.io/checklists/prompt-design-for-financial-extraction-checklist/
  Description: Financial extraction prompt checklist: enforce a strict schema, require source grounding, handle missing values, and test adversarial filings.
  Updated: 2026-05-26
- Prompt Injection Defense for Finance Agents: https://aifinhub.io/checklists/prompt-injection-defense-finance-checklist/
  Description: Prompt injection defense checklist: treat retrieved data as untrusted, isolate instructions, least-privilege tools, and red-team the pipeline.
  Updated: 2026-05-26
- RAG for Filings Setup Checklist: https://aifinhub.io/checklists/rag-for-filings-setup-checklist/
  Description: RAG for filings checklist: chunk on structure, tune retrieval, enforce citations, verify numbers, and treat retrieved text as untrusted.
  Updated: 2026-05-26
- Risk Model Validation Checklist: https://aifinhub.io/checklists/risk-model-validation-checklist/
  Description: Risk model validation checklist: backtest VaR with Kupiec and Christoffersen, check breach independence, validate fat tails, and stress the model.
  Updated: 2026-05-26
- Trading Strategy Validation Checklist: https://aifinhub.io/checklists/strategy-validation-checklist/
  Description: A sign-off checklist for validating a trading strategy before risking capital: data hygiene, out-of-sample testing, trial accounting, deflated Sharpe, and risk backtests.
  Updated: 2026-05-26
- Walk-Forward Validation Setup Checklist: https://aifinhub.io/checklists/walk-forward-validation-setup-checklist/
  Description: Walk-forward validation setup checklist: choose window mode, set an embargo, refit per slice, and read efficiency before trusting an OOS curve.
  Updated: 2026-05-26

### Comparisons (30)
- Arithmetic vs Logarithmic Returns: https://aifinhub.io/compare/arithmetic-vs-logarithmic-returns/
  Description: Arithmetic vs log returns decision matrix: time aggregation, cross-asset aggregation, compounding, and which return definition to use when.
  Updated: 2026-05-26
- Block Bootstrap vs IID Bootstrap: https://aifinhub.io/compare/block-bootstrap-vs-iid-bootstrap/
  Description: Block bootstrap vs IID bootstrap decision matrix: serial correlation, volatility clustering, block length, and which resampling fits returns.
  Updated: 2026-05-26
- Brier Score vs Log Loss: https://aifinhub.io/compare/brier-score-vs-log-loss/
  Description: Brier score vs log loss decision matrix for scoring probabilistic forecasts: penalty shape, sensitivity to confident errors, and which to use.
  Updated: 2026-05-26
- Calmar vs MAR Ratio: https://aifinhub.io/compare/calmar-vs-mar-ratio/
  Description: Calmar vs MAR ratio decision matrix: lookback window, drawdown denominator, track-record length, and which return-to-drawdown metric to report.
  Updated: 2026-05-26
- Cohen's Kappa vs ICC for Agreement: https://aifinhub.io/compare/cohen-kappa-vs-icc-agreement/
  Description: Cohen's kappa vs intraclass correlation decision matrix: categorical versus continuous ratings, chance correction, rater count, and which to use.
  Updated: 2026-05-26
- Cosine vs Euclidean Similarity: https://aifinhub.io/compare/cosine-vs-euclidean-similarity/
  Description: Cosine vs Euclidean distance decision matrix for embeddings: magnitude sensitivity, normalization, and which metric to use for vector search.
  Updated: 2026-05-26
- Dollar-Cost Averaging vs Lump-Sum Investing: https://aifinhub.io/compare/dollar-cost-averaging-vs-lump-sum/
  Description: Dollar-cost averaging vs lump-sum decision matrix: expected return, regret risk, time in market, and which cash-deployment strategy fits.
  Updated: 2026-05-26
- Embedding vs BM25 Retrieval: https://aifinhub.io/compare/embedding-vs-bm25-retrieval/
  Description: Embedding vs BM25 retrieval decision matrix for financial RAG: semantic recall, exact-term matching, cost, and which retriever for filings.
  Updated: 2026-05-26
- Fixed vs Trailing Stops: https://aifinhub.io/compare/fixed-vs-trailing-stops/
  Description: Fixed vs trailing stop-loss decision matrix: profit protection, whipsaw risk, trend capture, and which exit rule fits trend or mean reversion.
  Updated: 2026-05-26
- Full Revaluation vs Delta-Gamma VaR: https://aifinhub.io/compare/full-revaluation-vs-delta-gamma-var/
  Description: Full revaluation vs delta-gamma decision matrix for option VaR: nonlinear-payoff accuracy, compute cost, and which approximation to use.
  Updated: 2026-05-26
- GBM vs Jump-Diffusion Price Models: https://aifinhub.io/compare/gbm-vs-jump-diffusion/
  Description: GBM vs jump-diffusion decision matrix for synthetic prices: tail behavior, gap risk, calibration cost, and which process to simulate for backtests.
  Updated: 2026-05-26
- Greedy vs Beam Search Decoding: https://aifinhub.io/compare/greedy-vs-beam-search-decoding/
  Description: Greedy vs beam search decoding decision matrix for LLM extraction: determinism, sequence quality, cost, and which decoder to use for output.
  Updated: 2026-05-26
- Historical vs Parametric VaR: https://aifinhub.io/compare/historical-vs-parametric-var/
  Description: Historical vs parametric VaR decision matrix: distribution assumptions, fat-tail handling, speed, and which estimation method fits your book.
  Updated: 2026-05-26
- In-Sample vs Out-of-Sample Testing: https://aifinhub.io/compare/in-sample-vs-out-of-sample/
  Description: In-sample vs out-of-sample decision matrix: what each measures, optimism bias, overfitting detection, and how to split backtest data honestly.
  Updated: 2026-05-26
- JSON Mode vs Tool Calling for Extraction: https://aifinhub.io/compare/json-mode-vs-tool-calling-extraction/
  Description: JSON mode vs tool calling decision matrix for structured LLM extraction: schema enforcement, validity guarantees, multi-field control, and which to use.
  Updated: 2026-05-26
- Max Drawdown vs Ulcer Index: https://aifinhub.io/compare/max-drawdown-vs-ulcer-index/
  Description: Max drawdown vs Ulcer Index decision matrix: single worst loss versus sustained pain, sensitivity to one event, and which drawdown metric to report.
  Updated: 2026-05-26
- Mean-Variance vs Risk-Parity Allocation: https://aifinhub.io/compare/mean-variance-vs-risk-parity/
  Description: Mean-variance vs risk-parity decision matrix: return-forecast dependence, estimation error, leverage, and which method to allocate with.
  Updated: 2026-05-26
- Monte Carlo vs Historical VaR: https://aifinhub.io/compare/monte-carlo-vs-historical-var/
  Description: Monte Carlo vs historical VaR decision matrix: model dependence, nonlinear payoffs, scenario coverage, and which simulation method to trust.
  Updated: 2026-05-26
- Paper vs Live Trading: https://aifinhub.io/compare/paper-vs-live-trading/
  Description: Paper vs live trading decision matrix: fill realism, slippage, latency, psychology, and what a paper account proves before risking real capital.
  Updated: 2026-05-26
- Platt vs Temperature Scaling: https://aifinhub.io/compare/platt-vs-temperature-scaling/
  Description: Platt vs temperature scaling decision matrix for confidence calibration: parameters fit, multiclass behavior, and when each one fits best.
  Updated: 2026-05-26
- Point Estimate vs Prediction Interval: https://aifinhub.io/compare/point-estimate-vs-prediction-interval/
  Description: Point estimate vs prediction interval decision matrix: single number versus quantified uncertainty, calibration, and which to report when.
  Updated: 2026-05-26
- Realized vs Implied Volatility: https://aifinhub.io/compare/realized-vs-implied-volatility/
  Description: Realized vs implied volatility decision matrix: backward versus forward looking, the variance risk premium, what each measures, and which to use when.
  Updated: 2026-05-26
- Self-Consistency vs Single-Pass Inference: https://aifinhub.io/compare/self-consistency-vs-single-pass/
  Description: Self-consistency vs single-pass decision matrix for LLM tasks: reasoning accuracy, cost multiplier, and when sampling-and-voting pays off.
  Updated: 2026-05-26
- Semantic vs Recursive Chunking: https://aifinhub.io/compare/semantic-vs-recursive-chunking/
  Description: Semantic vs recursive chunking decision matrix for filing RAG: boundary quality, cost, determinism, and which splitting strategy to use.
  Updated: 2026-05-26
- Sharpe Ratio vs Sortino Ratio: https://aifinhub.io/compare/sharpe-ratio-vs-sortino-ratio/
  Description: A decision matrix comparing the Sharpe and Sortino ratios: what each penalizes, when they diverge, their assumptions, and which to report for a given return profile.
  Updated: 2026-05-26
- Simple vs Exponential Moving Average: https://aifinhub.io/compare/simple-vs-exponential-moving-average/
  Description: SMA vs EMA decision matrix: lag, responsiveness, weighting of recent data, drop-off artifacts, and which moving average fits a signal or smoothing task.
  Updated: 2026-05-26
- Value-Weighted vs Equal-Weighted Index: https://aifinhub.io/compare/value-weighted-vs-equal-weighted-index/
  Description: Value-weighted vs equal-weighted index decision matrix: concentration, factor tilts, rebalancing cost, and which weighting to benchmark with.
  Updated: 2026-05-26
- VaR vs CVaR (Expected Shortfall): https://aifinhub.io/compare/var-vs-cvar/
  Description: VaR vs CVaR decision matrix: what each measures, tail sensitivity, coherence, regulatory status, and which risk number to report for a fat-tailed book.
  Updated: 2026-05-26
- Walk-Forward vs K-Fold Cross-Validation: https://aifinhub.io/compare/walk-forward-vs-k-fold-cross-validation/
  Description: A decision matrix comparing walk-forward analysis and k-fold cross-validation for financial backtesting: leakage, regime handling, data efficiency, and when each fits.
  Updated: 2026-05-26
- Zero-Shot vs Few-Shot Extraction: https://aifinhub.io/compare/zero-shot-vs-few-shot-extraction/
  Description: Zero-shot vs few-shot prompting decision matrix for filing extraction: accuracy, token cost, format control, and which approach to choose.
  Updated: 2026-05-26

### Alternatives (9)
- Alpaca API Alternatives (2026): https://aifinhub.io/alternatives/alpaca-api-alternatives-2026/
  Description: Alpaca trading API alternatives in 2026: Tradier, Interactive Brokers, Charles Schwab, and Tradestation compared on commissions, rate limits, auth, and asset coverage.
  Updated: 2026-05-26
- Alpha Vantage Alternatives (2026): https://aifinhub.io/alternatives/alpha-vantage-alternatives-2026/
  Description: Alpha Vantage alternatives in 2026: Finnhub, Twelve Data, Financial Modeling Prep, EODHD, and Tiingo compared on free-tier limits, rate caps, fundamentals, and coverage.
  Updated: 2026-05-26
- Databento Alternatives (2026): https://aifinhub.io/alternatives/databento-alternatives-2026/
  Description: Databento alternatives for market data in 2026: Polygon.io, Alpaca, Tardis, and direct exchange feeds compared on price, coverage, and latency.
  Updated: 2026-05-26
- EODHD Alternatives (2026): https://aifinhub.io/alternatives/eodhd-alternatives-2026/
  Description: EODHD alternatives in 2026: Financial Modeling Prep, Tiingo, Twelve Data, Polygon, and Alpha Vantage compared on global coverage, fundamentals, intraday depth, and cost.
  Updated: 2026-05-26
- Finnhub Alternatives (2026): https://aifinhub.io/alternatives/finnhub-alternatives-2026/
  Description: Finnhub alternatives in 2026: Twelve Data, Financial Modeling Prep, EODHD, Tiingo, and Alpha Vantage compared on free tiers, real-time data, fundamentals, and coverage.
  Updated: 2026-05-26
- Interactive Brokers (IBKR) API Alternatives (2026): https://aifinhub.io/alternatives/ibkr-api-alternatives-2026/
  Description: IBKR API alternatives in 2026: Alpaca, Tradier, Charles Schwab, and Tradestation compared on auth, asset coverage, integration weight, commissions, and MCP support.
  Updated: 2026-05-26
- Pinecone Alternatives (2026): https://aifinhub.io/alternatives/pinecone-alternatives-2026/
  Description: Pinecone alternatives in 2026 for financial RAG: Qdrant, Weaviate, Milvus, Chroma, and pgvector compared on cost at scale, self-hosting, hybrid search, and ops burden.
  Updated: 2026-05-26
- Polygon.io (Massive) Alternatives (2026): https://aifinhub.io/alternatives/polygon-massive-alternatives-2026/
  Description: Polygon.io (now Massive) alternatives for market data in 2026: Databento, Alpaca, Tiingo, and Financial Modeling Prep compared on price, coverage, and real-time access.
  Updated: 2026-05-26
- Tiingo Alternatives (2026): https://aifinhub.io/alternatives/tiingo-alternatives-2026/
  Description: Tiingo alternatives in 2026: EODHD, Financial Modeling Prep, Twelve Data, Alpha Vantage, and Polygon compared on history depth, global coverage, fundamentals, and cost.
  Updated: 2026-05-26

### Learn (30)
- Agent Skill Testing: https://aifinhub.io/learn/agent-skill-testing/
  Description: Agent skill testing: the regression-test discipline for LLM-driven agents. What to test, how to score, and the difference between pass-rate and capability.
  Updated: 2026-05-10
- Agent-Cost Envelope: https://aifinhub.io/learn/agent-cost-envelope/
  Description: The agent-cost envelope: the loop of (calls × tokens × retries × model_price) that determines the dollar cost of an LLM-driven trading agent per decision.
  Updated: 2026-05-10
- Alpha: https://aifinhub.io/learn/alpha/
  Description: Alpha as risk-adjusted excess return: definition, the beta-adjustment math, and why most claimed alpha disappears once you adjust for the right factors.
  Updated: 2026-05-10
- Bailey-Lopez de Prado PBO: https://aifinhub.io/learn/bailey-lopez-pbo/
  Description: Probability of Backtest Overfitting: a combinatorial test that estimates how likely your best in-sample strategy is to underperform out-of-sample.
  Updated: 2026-05-10
- Beta: https://aifinhub.io/learn/beta/
  Description: Beta as factor sensitivity: what it measures, why a beta of 1 doesn't mean 'tracks the market', and the rolling-vs-static distinction that catches most people.
  Updated: 2026-05-10
- Bid-Ask Spread: https://aifinhub.io/learn/bid-ask-spread/
  Description: Bid-ask spread defined: quoted vs effective vs realized spread, why the touch isn't the cost you actually pay, and how to measure each.
  Updated: 2026-05-10
- Drawdown: https://aifinhub.io/learn/drawdown/
  Description: Drawdown explained: peak-to-trough decline, why max drawdown alone is misleading, and the recovery math that actually matters.
  Updated: 2026-05-10
- Expected Shortfall (CVaR): https://aifinhub.io/learn/expected-shortfall/
  Description: Expected shortfall: the average loss given a VaR breach. Why regulators are migrating from VaR and what ES catches that VaR misses.
  Updated: 2026-05-10
- FAQPage Schema: https://aifinhub.io/learn/faqpage-schema/
  Description: Schema.org FAQPage: the structured-data spec that makes FAQ content machine-readable for search and LLM crawlers. When to apply, when to skip.
  Updated: 2026-05-10
- Hallucination Detection: https://aifinhub.io/learn/hallucination-detection/
  Description: Detecting LLM hallucinations in financial outputs: the verifiable-claim approach, citation grounding, and cross-model agreement signals that work.
  Updated: 2026-05-10
- HowTo Schema: https://aifinhub.io/learn/howto-schema/
  Description: Schema.org HowTo: the structured-data type for step-by-step procedural content. The fields that matter for agent ingestion vs the ones search ignores.
  Updated: 2026-05-10
- Kelly Criterion: https://aifinhub.io/learn/kelly-criterion/
  Description: What the Kelly criterion is, when full Kelly blows up, and why most working quants size at half- or quarter-Kelly.
  Updated: 2026-05-10
- Latency Arbitrage: https://aifinhub.io/learn/latency-arbitrage/
  Description: Latency arbitrage: cross-venue price discrepancies exploited by being faster than the slowest replicator. Why the game is mostly won at the cable layer.
  Updated: 2026-05-10
- Look-Ahead Bias: https://aifinhub.io/learn/look-ahead-bias/
  Description: Look-ahead bias: when a backtest accidentally uses data the strategy wouldn't have had at decision time. The most common variants and how to catch them.
  Updated: 2026-05-10
- Maker-Taker: https://aifinhub.io/learn/maker-taker/
  Description: Maker-taker fee model: makers get a rebate, takers pay. Why the model exists, what it incentivizes, and how to size up real net cost.
  Updated: 2026-05-10
- MCP (Model Context Protocol): https://aifinhub.io/learn/model-context-protocol/
  Description: Model Context Protocol: Anthropic's open standard for letting LLMs discover and call tools — the interface, why it matters, and finance MCP server checks.
  Updated: 2026-05-10
- Model Drift: https://aifinhub.io/learn/model-drift/
  Description: Model drift: when an LLM's behavior changes between calls, versions, or weeks. The monitoring stack that catches it before production breaks.
  Updated: 2026-05-10
- Monte Carlo Simulation: https://aifinhub.io/learn/monte-carlo-simulation/
  Description: Monte Carlo simulation in trading: when it's the right tool, when it's overkill, and the seed-discipline gotcha that ruins most published examples.
  Updated: 2026-05-10
- Order Book Imbalance: https://aifinhub.io/learn/order-book-imbalance/
  Description: Order book imbalance: definition, the depth-weighting choice that changes everything, and why it predicts short-horizon price moves more than fundamentals.
  Updated: 2026-05-10
- Overfitting: https://aifinhub.io/learn/overfitting/
  Description: Overfitting in trading-strategy backtests: how multiple-testing inflates apparent edges and the diagnostics that catch it.
  Updated: 2026-05-10
- Prompt Injection: https://aifinhub.io/learn/prompt-injection/
  Description: Prompt injection: when untrusted text in a prompt overrides system instructions. The attack patterns and the structural defenses that work in production.
  Updated: 2026-05-10
- Regulatory Cost of AI in Finance: https://aifinhub.io/learn/regulatory-cost-ai-finance/
  Description: Regulatory cost as a function of jurisdiction, model class, and end-use: the FTC vs NLT distinction and the documentation burden by regime.
  Updated: 2026-05-10
- Sharpe Ratio: https://aifinhub.io/learn/sharpe-ratio/
  Description: Sharpe ratio defined, when it lies (skew, fat tails, autocorrelation), and how to read a Sharpe number you didn't compute yourself.
  Updated: 2026-05-10
- Sharpe vs Sortino: https://aifinhub.io/learn/sharpe-vs-sortino/
  Description: Sharpe vs Sortino: when the gap between the two tells you something real about a strategy's tail behaviour — and when it's just noise from a small sample.
  Updated: 2026-05-10
- Slippage: https://aifinhub.io/learn/slippage/
  Description: Slippage as the gap between expected and executed price: the components (spread, market impact, latency), and how to model each in a backtest.
  Updated: 2026-05-10
- Sortino Ratio: https://aifinhub.io/learn/sortino-ratio/
  Description: Sortino ratio: same numerator as Sharpe, denominator only counts downside volatility. When it's the right number to look at.
  Updated: 2026-05-10
- Survivorship Bias: https://aifinhub.io/learn/survivorship-bias/
  Description: Survivorship bias in backtests: why dropped tickers, delisted funds, and dead share classes systematically inflate historical returns.
  Updated: 2026-05-10
- Value at Risk (VaR): https://aifinhub.io/learn/value-at-risk/
  Description: Value at Risk: the loss threshold you'll exceed with probability α. Why historical VaR is brittle and what it doesn't tell you about the tail.
  Updated: 2026-05-10
- Volatility: https://aifinhub.io/learn/volatility/
  Description: Volatility as the standard deviation of returns: realized vs implied, the annualization gotcha, and why volatility-of-volatility matters.
  Updated: 2026-05-10
- Walk-Forward Optimization: https://aifinhub.io/learn/walk-forward-optimization/
  Description: Walk-forward optimization: rolling-window train/test that mimics live deployment. Why anchored vs sliding matters and the gotchas in window sizing.
  Updated: 2026-05-10

### Formulas (39)
- Annualized Volatility Formula: https://aifinhub.io/formulas/annualized-volatility-formula/
  Description: The annualized volatility formula scales per-period return standard deviation by the square root of periods per year. Root-time scaling explained.
  Updated: 2026-05-26
- Beta Formula: https://aifinhub.io/formulas/beta-formula/
  Description: The beta formula: covariance of asset and market returns over market variance. The CAPM regression slope measuring systematic risk, with an example.
  Updated: 2026-05-26
- CAGR Formula: https://aifinhub.io/formulas/cagr-formula/
  Description: The CAGR formula: the constant annual rate growing a beginning value to an ending value over n years. The true geometric return, with a worked example.
  Updated: 2026-05-26
- Calmar Ratio Formula: https://aifinhub.io/formulas/calmar-ratio-formula/
  Description: The Calmar ratio formula: annualized return divided by maximum drawdown over the period. A drawdown-based risk-adjusted return with a worked example.
  Updated: 2026-05-26
- CAPM Formula: https://aifinhub.io/formulas/capm-formula/
  Description: The CAPM formula: expected return equals the risk-free rate plus beta times the market risk premium. The basis for pricing systematic risk.
  Updated: 2026-05-26
- Correlation Formula: https://aifinhub.io/formulas/correlation-formula/
  Description: The Pearson correlation formula: covariance of two return series over the product of their standard deviations. The key diversification input.
  Updated: 2026-05-26
- Cost Per 1K Tokens Formula: https://aifinhub.io/formulas/cost-per-1k-tokens-formula/
  Description: The cost-per-1K-tokens formula: input tokens times input price plus output tokens times output price. Why output dominates LLM cost, with an example.
  Updated: 2026-05-26
- Cost Per Validated Trade Formula: https://aifinhub.io/formulas/cost-per-validated-trade-formula/
  Description: The cost-per-validated-trade formula: total LLM spend over trades that pass validation. The real unit economics of an AI trading agent.
  Updated: 2026-05-26
- CVaR / Expected Shortfall Formula: https://aifinhub.io/formulas/cvar-expected-shortfall-formula/
  Description: The CVaR formula: the average loss in the worst tail beyond VaR. Expected shortfall, a coherent risk measure favored by Basel, with a worked example.
  Updated: 2026-05-26
- Deflated Sharpe Ratio Formula: https://aifinhub.io/formulas/deflated-sharpe-ratio-formula/
  Description: The deflated Sharpe ratio formula: the probability a strategy's Sharpe is real after correcting for the number of trials, return skew, kurtosis, and sample length.
  Updated: 2026-05-26
- Downside Deviation Formula: https://aifinhub.io/formulas/downside-deviation-formula/
  Description: The downside deviation formula: root mean square of returns below a target, over total observations. The risk term inside the Sortino ratio.
  Updated: 2026-05-26
- Expectancy Formula: https://aifinhub.io/formulas/expectancy-formula/
  Description: The expectancy formula: win rate times average win minus loss rate times average loss. The expected profit per trade in R-multiples, with an example.
  Updated: 2026-05-26
- Fractional Kelly Formula: https://aifinhub.io/formulas/fractional-kelly-formula/
  Description: The fractional Kelly formula stakes a fixed multiple of full Kelly to cut volatility for a small growth cost. Why half-Kelly is popular.
  Updated: 2026-05-26
- Fundamental Law of Active Management Formula: https://aifinhub.io/formulas/fundamental-law-active-management-formula/
  Description: The fundamental law of active management: information ratio equals information coefficient times the square root of breadth. With an example.
  Updated: 2026-05-26
- Gain-to-Pain Ratio Formula: https://aifinhub.io/formulas/gain-to-pain-ratio-formula/
  Description: The gain-to-pain ratio formula: sum of returns over the absolute sum of losing periods. A robust Schwager measure of return per unit of pain.
  Updated: 2026-05-26
- Historical VaR Formula: https://aifinhub.io/formulas/historical-var-formula/
  Description: The historical VaR formula: the empirical quantile of past returns at a confidence level. A distribution-free Value-at-Risk method, with an example.
  Updated: 2026-05-26
- Information Coefficient Formula: https://aifinhub.io/formulas/information-coefficient-formula/
  Description: The information coefficient formula: correlation between forecast and realized returns. How to measure quant forecasting skill, with a worked example.
  Updated: 2026-05-26
- Information Ratio Formula: https://aifinhub.io/formulas/information-ratio-formula/
  Description: The information ratio formula: active return over a benchmark divided by tracking error. Measures the consistency of excess return, with an example.
  Updated: 2026-05-26
- Jensen's Alpha Formula: https://aifinhub.io/formulas/jensens-alpha-formula/
  Description: Jensen's alpha formula: realized return minus the CAPM-expected return given beta. The excess return a manager earns beyond market risk.
  Updated: 2026-05-26
- Kelly Criterion Formula: https://aifinhub.io/formulas/kelly-criterion-formula/
  Description: The Kelly criterion formula: the bet fraction maximizing long-run log growth from win probability and payoff odds. The optimal sizing rule.
  Updated: 2026-05-26
- Kurtosis Formula: https://aifinhub.io/formulas/kurtosis-formula/
  Description: The kurtosis formula: the fourth standardized moment of returns. Measures tail heaviness, with excess kurtosis relative to the normal, and an example.
  Updated: 2026-05-26
- M-Squared (M2) Formula: https://aifinhub.io/formulas/m-squared-formula/
  Description: The M-squared formula: the return a portfolio earns if levered to market volatility. Modigliani risk-adjusted performance in return units.
  Updated: 2026-05-26
- Maximum Drawdown Formula: https://aifinhub.io/formulas/max-drawdown-formula/
  Description: The maximum drawdown formula: the largest peak-to-trough decline in an equity curve. The worst loss from a prior high, with a worked example.
  Updated: 2026-05-26
- Omega Ratio Formula: https://aifinhub.io/formulas/omega-ratio-formula/
  Description: The Omega ratio formula: probability-weighted gains above a threshold over losses below it. Uses the whole return distribution, with a worked example.
  Updated: 2026-05-26
- Parametric VaR Formula: https://aifinhub.io/formulas/parametric-var-formula/
  Description: The parametric VaR formula: Value-at-Risk from the mean, volatility, and a normal z-score. The variance-covariance method, with a worked example.
  Updated: 2026-05-26
- Portfolio Turnover Formula: https://aifinhub.io/formulas/turnover-formula/
  Description: The portfolio turnover formula: the lesser of purchases or sales over average assets. How turnover drives transaction costs and tax drag.
  Updated: 2026-05-26
- Probabilistic Sharpe Ratio Formula: https://aifinhub.io/formulas/probabilistic-sharpe-ratio-formula/
  Description: The probabilistic Sharpe ratio formula: the chance a true Sharpe beats a benchmark, adjusting for skew, kurtosis, and sample length, with an example.
  Updated: 2026-05-26
- Probability of Backtest Overfitting (PBO) Formula: https://aifinhub.io/formulas/pbo-formula/
  Description: The PBO formula: the probability the best in-sample strategy lands below median out-of-sample, via combinatorial cross-validation. With an example.
  Updated: 2026-05-26
- Profit Factor Formula: https://aifinhub.io/formulas/profit-factor-formula/
  Description: The profit factor formula: gross profit divided by gross loss. A single number summarizing a strategy's edge, what values mean, with a worked example.
  Updated: 2026-05-26
- Prompt Cache Break-Even Formula: https://aifinhub.io/formulas/prompt-cache-break-even-formula/
  Description: The prompt-cache break-even formula: how many reuses of a cached prefix repay its write premium. When caching pays off for LLM workloads.
  Updated: 2026-05-26
- R-Squared Formula: https://aifinhub.io/formulas/r-squared-formula/
  Description: The R-squared formula: the share of a portfolio's return variance explained by its benchmark. The squared correlation behind beta and alpha.
  Updated: 2026-05-26
- Sharpe Ratio Formula: https://aifinhub.io/formulas/sharpe-ratio-formula/
  Description: The Sharpe ratio formula: excess return over the risk-free rate divided by return volatility, then annualized. Every variable defined, with a worked example.
  Updated: 2026-05-26
- Skewness Formula: https://aifinhub.io/formulas/skewness-formula/
  Description: The skewness formula: the third standardized moment of returns. Measures asymmetry, the tilt toward large gains or losses, with a worked example.
  Updated: 2026-05-26
- Sortino Ratio Formula: https://aifinhub.io/formulas/sortino-ratio-formula/
  Description: The Sortino ratio formula: excess return over a target divided by downside deviation, so only harmful volatility is penalized. With a worked example.
  Updated: 2026-05-26
- Sterling Ratio Formula: https://aifinhub.io/formulas/sterling-ratio-formula/
  Description: The Sterling ratio formula: annualized return over average annual drawdown plus a 10% penalty. A stricter drawdown-adjusted return, with an example.
  Updated: 2026-05-26
- Tracking Error Formula: https://aifinhub.io/formulas/tracking-error-formula/
  Description: The tracking error formula: the standard deviation of a portfolio's active return versus its benchmark. How tightly a fund tracks its index.
  Updated: 2026-05-26
- Treynor Ratio Formula: https://aifinhub.io/formulas/treynor-ratio-formula/
  Description: The Treynor ratio formula: excess return over the risk-free rate divided by beta. Reward per unit of systematic market risk, with a worked example.
  Updated: 2026-05-26
- Ulcer Index Formula: https://aifinhub.io/formulas/ulcer-index-formula/
  Description: The Ulcer Index formula: the root mean square of percentage drawdowns from running highs. Measures depth and duration of losses, with an example.
  Updated: 2026-05-26
- Win Rate Formula: https://aifinhub.io/formulas/win-rate-formula/
  Description: The win rate formula: winning trades divided by total trades. Why win rate alone is meaningless without the payoff ratio, with a breakeven example.
  Updated: 2026-05-26

### Examples (20)
- Agent Cost Envelope Calculator: Examples: https://aifinhub.io/examples/agent-cost-envelope-calculator-examples/
  Description: Worked examples sizing an LLM trading agent's monthly cost: tokens per step, steps per loop, markets per day and model choice against a budget envelope.
  Updated: 2026-05-26
- AI Finance Regulatory Cost: Worked Examples: https://aifinhub.io/examples/ftc-vs-nlt-regulatory-cost-examples/
  Description: Compliance-cost examples for an AI finance product across US, UK and EU regimes. Same workload, three jurisdictions, computed setup and annual cost.
  Updated: 2026-05-26
- Batch vs Realtime LLM Cost: Examples: https://aifinhub.io/examples/batch-vs-realtime-cost-calculator-examples/
  Description: Batch vs real-time LLM pricing examples for finance jobs. See when the 50 percent batch discount applies and when a tight deadline blocks it.
  Updated: 2026-05-26
- Deflated Sharpe Ratio: Worked Examples: https://aifinhub.io/examples/deflated-sharpe-ratio-examples/
  Description: Deflated Sharpe examples showing how backtest trial count haircuts a Sharpe ratio. Same observed Sharpe, more trials, lower chance the edge is real.
  Updated: 2026-05-27
- Earnings Call Summarization Cost: Examples: https://aifinhub.io/examples/earnings-call-summarization-cost-examples/
  Description: Worked LLM cost examples for summarizing earnings calls at scale. See annual spend per model for a 50-ticker universe, computed from list pricing.
  Updated: 2026-05-26
- Execution Cost Simulator: Worked Examples: https://aifinhub.io/examples/execution-simulator-examples/
  Description: Execution-cost examples: how order size, spread and participation set market impact in basis points, computed from a square-root impact model.
  Updated: 2026-05-26
- Financial Document Token Estimator: Examples: https://aifinhub.io/examples/financial-document-token-estimator-examples/
  Description: Worked token and cost examples for analyzing SEC filings with LLMs. See one-pass and multi-filing synthesis costs per model, computed from list pricing.
  Updated: 2026-05-26
- Kalshi-Polymarket Arbitrage: Examples: https://aifinhub.io/examples/kalshi-poly-arb-examples/
  Description: Cross-market arbitrage examples between Kalshi and Polymarket. See how fees and slippage turn a gross edge into the real net edge in basis points.
  Updated: 2026-05-26
- Kelly Sizer Worked Examples: https://aifinhub.io/examples/kelly-sizer-examples/
  Description: Worked Kelly criterion examples: how win probability and payoff ratio set the optimal bet fraction, and why practitioners scale down to half or quarter Kelly.
  Updated: 2026-05-27
- Market Data Vendor TCO: Worked Examples: https://aifinhub.io/examples/data-vendor-tco-examples/
  Description: Market-data vendor cost examples ranking vendors by annual cost. See how universe size, resolution and live data flip the cheapest option.
  Updated: 2026-05-26
- Options Greeks Explorer: Worked Examples: https://aifinhub.io/examples/options-greeks-explorer-examples/
  Description: Black-Scholes Greeks examples: how moneyness changes delta, gamma and vega for the same underlying, with every price computed from the closed-form.
  Updated: 2026-05-26
- Options Payoff Builder: Worked Examples: https://aifinhub.io/examples/options-payoff-builder-examples/
  Description: Option payoff examples: net premium, breakevens, max profit and loss for a call, a spread, a straddle and a short put, priced with Black-Scholes.
  Updated: 2026-05-27
- Position Sizing Under Edge Variance: Examples: https://aifinhub.io/examples/position-sizing-edge-variance-examples/
  Description: Bayesian-Kelly worked examples: how uncertainty about your edge shrinks the bet below deterministic Kelly. Every fraction computed from the closed-form.
  Updated: 2026-05-26
- Returns Distribution Analyzer: Examples: https://aifinhub.io/examples/returns-distribution-analyzer-examples/
  Description: Examples reading skew, kurtosis and the Jarque-Bera test on return series. See when a distribution looks normal and when a tail breaks it.
  Updated: 2026-05-26
- Risk-Adjusted Returns: Worked Examples: https://aifinhub.io/examples/risk-adjusted-returns-examples/
  Description: Sharpe, Sortino, Omega and Calmar worked examples from short daily return series. See exactly when each ratio agrees and when one quietly breaks.
  Updated: 2026-05-26
- SEC Filing Chunk Optimizer: Examples: https://aifinhub.io/examples/sec-filing-chunk-optimizer-examples/
  Description: RAG chunking examples for SEC filings: how chunk size, overlap and strategy set chunk count, embedding cost and the warnings that flag bad configs.
  Updated: 2026-05-26
- Sharpe vs Sortino Worked Examples: https://aifinhub.io/examples/sharpe-vs-sortino-examples/
  Description: Worked examples showing when Sharpe and Sortino diverge: same mean return, different volatility shapes. Every number computed from the standard annualized formulas.
  Updated: 2026-05-27
- Statistical Arbitrage Capacity: Examples: https://aifinhub.io/examples/statistical-arbitrage-capacity-examples/
  Description: Capacity examples for a stat-arb strategy: how alpha, market impact and slippage cap deployable AUM, with every figure from the impact model.
  Updated: 2026-05-27
- Token Cost Optimizer: Worked Examples: https://aifinhub.io/examples/token-cost-optimizer-examples/
  Description: LLM cost examples for a research loop: how model choice, caching and retries set cost per validated trade idea, computed from list pricing.
  Updated: 2026-05-26
- VaR Backtest (Kupiec, Christoffersen): Examples: https://aifinhub.io/examples/var-backtest-kupiec-christoffersen-examples/
  Description: Worked VaR backtest examples: Kupiec coverage and Christoffersen independence tests on exception counts. See the case where the right count still fails.
  Updated: 2026-05-26

### How To Use (45)
- How to use Agent Cost Envelope Calculator: https://aifinhub.io/calculator-guides/agent-cost-envelope-calculator/
  Description: Agent Cost Envelope: model end-to-end LLM loop. Steps, tool calls, convergence checks. Per-loop, daily, monthly cost with explicit cap.
  Updated: 2026-05-12
- How to use Agent Skill Tester for Markets: https://aifinhub.io/calculator-guides/agent-skill-tester/
  Description: Agent Skill Tester: paste SKILL.md and a sample. Runs in-browser, returns structured extraction, token cost, latency. Test skills before production.
  Updated: 2026-05-12
- How to use Backtest Overfitting Score: https://aifinhub.io/calculator-guides/backtest-overfitting-score/
  Description: Backtest Overfitting Score: upload trade logs. Get PBO, Deflated Sharpe, and probability of skill — quantify selection bias vs real edge.
  Updated: 2026-05-12
- How to use Batch vs Real-Time Cost Calculator: https://aifinhub.io/calculator-guides/batch-vs-realtime-cost-calculator/
  Description: Batch vs Real-Time Cost Calculator: jobs/day, tokens, model, deadline in. Side-by-side real-time vs batch cost with savings and SLA eligibility.
  Updated: 2026-05-12
- How to use Broker API Comparator: https://aifinhub.io/calculator-guides/broker-api-comparator/
  Description: Broker API Comparator: five retail brokers side-by-side on auth, rate limits, order types, market data, MCP, and fees — the integration-cost matrix.
  Updated: 2026-05-12
- How to use Calibration Dojo: https://aifinhub.io/calculator-guides/calibration-dojo/
  Description: Calibration Dojo: answer binary forecasting questions at any confidence level. Tracks Brier score and reliability curve — train probabilistic intuition.
  Updated: 2026-05-12
- How to use Cointegration Half-Life Solver: https://aifinhub.io/calculator-guides/cointegration-half-life-solver/
  Description: Cointegration Half-Life Solver: two price series. Engle-Granger ADF p-value, OU half-life, hedge ratio, and spread chart for stat-arb sizing.
  Updated: 2026-05-12
- How to use Correlation Matrix Visualizer: https://aifinhub.io/calculator-guides/correlation-matrix-visualizer/
  Description: Correlation Matrix Visualizer: multi-asset returns CSV. Heatmap plus condition number, mean-abs correlation, eigenvalue concentration diagnostics.
  Updated: 2026-05-12
- How to use Data-Vendor TCO Calculator: https://aifinhub.io/calculator-guides/data-vendor-tco/
  Description: Data Vendor TCO: enter instrument count, bar resolution, history depth. Get annual cost across six retail data vendors side-by-side.
  Updated: 2026-05-12
- How to use Deflated Sharpe Ratio Calculator: https://aifinhub.io/calculator-guides/deflated-sharpe-ratio/
  Description: Deflated Sharpe Ratio: observed Sharpe, sample length, K trials in. Returns Bailey-Lopez de Prado deflated Sharpe and PSR (probability of skill).
  Updated: 2026-05-12
- How to use Drawdown-Recovery Markov Simulator: https://aifinhub.io/calculator-guides/drawdown-recovery-markov/
  Description: Drawdown Recovery (Markov + Cornish-Fisher MC): drawdown depth, Sharpe, skew, kurtosis in. Recovery time distribution over thousands of simulations.
  Updated: 2026-05-12
- How to use Earnings-Call Summarization Cost Calculator: https://aifinhub.io/calculator-guides/earnings-call-summarization-cost/
  Description: Earnings Call Summarization Cost: per-stock per-quarter LLM cost across Sonnet, Opus, GPT-4o, Gemini Pro/Flash. Cache-aware, snapshot pricing.
  Updated: 2026-05-12
- How to use Efficient Frontier Builder: https://aifinhub.io/calculator-guides/efficient-frontier-builder/
  Description: Efficient Frontier Builder: multi-asset returns CSV. Markowitz mean-variance frontier, min-variance and tangency portfolios with actual weights.
  Updated: 2026-05-12
- How to use Execution Simulator: https://aifinhub.io/calculator-guides/execution-simulator/
  Description: Execution Simulator: order params + venue config. Models sqrt-impact, latency, partial fills, queue position. Outputs realistic fill vs naive slippage.
  Updated: 2026-05-12
- How to use Fallback Chain Simulator: https://aifinhub.io/calculator-guides/fallback-chain-simulator/
  Description: Fallback Chain Simulator: provider chain in. Rate-limit + latency failures simulated. Outputs p50/p95/p99 latency, success rate, cost, degradations.
  Updated: 2026-05-12
- How to use Finance MCP Directory: https://aifinhub.io/calculator-guides/finance-mcp-directory/
  Description: Finance MCP Directory: side-by-side audit of seven trading-related MCP servers across auth, idempotency, transport, and schema strictness.
  Updated: 2026-05-12
- How to use Financial Document Token Estimator: https://aifinhub.io/calculator-guides/financial-document-token-estimator/
  Description: Financial Document Token Estimator: paste a filing or transcript. Token count plus one-pass extraction cost across 10 frontier LLMs, cache-aware.
  Updated: 2026-05-12
- How to use Forecast Scoring Sandbox: https://aifinhub.io/calculator-guides/forecast-scoring-sandbox/
  Description: Forecast Scoring Sandbox: (probability, outcome) pairs in. Brier with decomposition, log loss, reliability diagram, bootstrap CIs out.
  Updated: 2026-05-12
- How to use Fractional Kelly Sizer: https://aifinhub.io/calculator-guides/kelly-sizer/
  Description: Kelly Sizer: enter win probability, win/loss ratio, and Kelly fraction. Get bet size, drawdown distribution, and ruin rate via Monte Carlo.
  Updated: 2026-05-12
- How to use FTC vs FCA vs MiCA+DORA Regulatory Cost: https://aifinhub.io/calculator-guides/ftc-vs-nlt-regulatory-cost/
  Description: Regulatory Cost Comparator: pick product type + jurisdictions (FTC/FCA/MiCA/DORA). Outputs compliance cost snapshot with as-of date for each.
  Updated: 2026-05-12
- How to use Hallucination Detector: https://aifinhub.io/calculator-guides/hallucination-detector/
  Description: Hallucination Detector: source document plus LLM extraction. Numeric claims matched line-by-line, fabricated numbers flagged before reaching production.
  Updated: 2026-05-12
- How to use Kalshi vs Polymarket Arb Scanner: https://aifinhub.io/calculator-guides/kalshi-poly-arb/
  Description: Kalshi/Polymarket Arb Scan: paired contracts across both venues, daily-refreshed. Gross edge, tax-adjusted edge, and resolution-risk overlay included.
  Updated: 2026-05-12
- How to use LLM Finance Error Taxonomy: https://aifinhub.io/calculator-guides/llm-finance-error-taxonomy/
  Description: LLM Finance Error Taxonomy: 12 documented failure modes. Paste LLM output, see which categories trigger — fast triage for finance pipelines.
  Updated: 2026-05-12
- How to use Model Selector for Finance: https://aifinhub.io/calculator-guides/model-selector-finance/
  Description: Model Selector: task, latency, cost, context, quality in. Ranked LLM recommendations with benchmark-grounded rationale per model.
  Updated: 2026-05-12
- How to use Options Greeks Explorer: https://aifinhub.io/calculator-guides/options-greeks-explorer/
  Description: Options Greeks Explorer: Black-Scholes pricer plus live delta, gamma, theta, vega, rho. Drag spot, strike, vol, DTE to build Greek intuition.
  Updated: 2026-05-12
- How to use Options Payoff Builder: https://aifinhub.io/calculator-guides/options-payoff-builder/
  Description: Options Payoff Builder: 1–4 leg strategy editor. Picks call/put, long/short, strikes. Renders at-expiry payoff, break-evens, max profit/loss.
  Updated: 2026-05-12
- How to use Order Book Replay Visualizer: https://aifinhub.io/calculator-guides/order-book-replay/
  Description: Order Book Replay: drop a Level-2 CSV. Reconstructs the book tick by tick with depth animation, spread over time, and imbalance signal.
  Updated: 2026-05-12
- How to use Pair Trading Cointegration Tester: https://aifinhub.io/calculator-guides/pair-trading-tester/
  Description: Pair Trading Tester: two price series in. Engle-Granger test, OU half-life, z-score plot — pair mean-reverts on a usable timescale or it doesn't.
  Updated: 2026-05-12
- How to use Position Sizing under Edge Variance: https://aifinhub.io/calculator-guides/position-sizing-edge-variance/
  Description: Position Sizing with Edge Variance: edge estimate, variance, sample size in. Deterministic, Bayesian-adjusted, and conservative-bound Kelly bet sizes.
  Updated: 2026-05-12
- How to use Price-Blind Research Auditor: https://aifinhub.io/calculator-guides/price-blind-auditor/
  Description: Price-Blind Auditor: paste an agent prompt or context. Flags price numbers, direction-leaking phrases, and outcome cues that cause LLM confabulation.
  Updated: 2026-05-12
- How to use Prompt Injection Tester: https://aifinhub.io/calculator-guides/prompt-injection-tester/
  Description: Prompt Injection Tester: 24 attacks against your finance agent — direct override, role-confusion, indirect-via-RAG. Each attack scored followed/refused.
  Updated: 2026-05-12
- How to use Prompt Regression Tester: https://aifinhub.io/calculator-guides/prompt-regression-tester/
  Description: Prompt Regression Tester: same prompt, multiple models. Diffs outputs and surfaces silent drift after provider model updates — catch regressions early.
  Updated: 2026-05-12
- How to use Quant Interview Question Generator: https://aifinhub.io/calculator-guides/quant-interview-question-generator/
  Description: Quant Interview Question Generator: pick topic + difficulty. Seeded for reproducibility, human-authored questions across five quant interview domains.
  Updated: 2026-05-12
- How to use Returns Distribution Analyzer: https://aifinhub.io/calculator-guides/returns-distribution-analyzer/
  Description: Returns Distribution Analyzer: returns CSV in. Histogram with normal overlay, QQ plot, skew, kurtosis, Jarque-Bera, tail-weight index out.
  Updated: 2026-05-12
- How to use Risk-Adjusted Returns Calculator: https://aifinhub.io/calculator-guides/risk-adjusted-returns/
  Description: Risk-Adjusted Returns: paste returns CSV. Computes Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, drawdown, and tail moments.
  Updated: 2026-05-12
- How to use SEC Filing Chunk Optimizer: https://aifinhub.io/calculator-guides/sec-filing-chunk-optimizer/
  Description: SEC Filing Chunk Optimizer: filing archetype, chunk size, overlap. Outputs chunk count, embedding cost, boundary warnings (tables, sections).
  Updated: 2026-05-12
- How to use Sharpe vs Sortino Calculator: https://aifinhub.io/calculator-guides/sharpe-vs-sortino-calculator/
  Description: Sharpe vs Sortino Calculator: daily returns in. Sharpe, Sortino, Calmar, Omega side-by-side. Recommendation on which ratio matches the distribution.
  Updated: 2026-05-12
- How to use Statistical Arbitrage Capacity Calculator: https://aifinhub.io/calculator-guides/statistical-arbitrage-capacity/
  Description: Stat-Arb Capacity: signal half-life, daily volume, slippage, fees, target Sharpe in. Sqrt-impact closed-form returns max AUM the strategy survives.
  Updated: 2026-05-12
- How to use Structured Schema Validator for Finance: https://aifinhub.io/calculator-guides/structured-schema-validator-finance/
  Description: Structured Schema Validator: LLM JSON in. Validates against four finance schemas. Sanity checks: currency, ticker, magnitude beyond JSON-Schema.
  Updated: 2026-05-12
- How to use Synthetic Market Data Generator: https://aifinhub.io/calculator-guides/synthetic-market-data-generator/
  Description: Synthetic Market Data Generator: pick GBM, GARCH, regime-switching, or copula-linked. Outputs price series for backtest stress-tests on controlled inputs.
  Updated: 2026-05-12
- How to use Token-Cost Optimizer: https://aifinhub.io/calculator-guides/token-cost-optimizer/
  Description: Token Cost Optimizer: prompt length, response length, model, retry rate, calls/day. Outputs monthly cost across major LLMs side-by-side.
  Updated: 2026-05-12
- How to use Trading System Blueprinter: https://aifinhub.io/calculator-guides/trading-system-blueprinter/
  Description: Trading System Blueprinter: pick data, LLM, broker, storage, risk, logger. Emits architecture diagram, repo scaffold ZIP, and decision checklist.
  Updated: 2026-05-12
- How to use VaR Backtest — Kupiec & Christoffersen: https://aifinhub.io/calculator-guides/var-backtest-kupiec-christoffersen/
  Description: VaR Backtest (Kupiec + Christoffersen): P&L and VaR series in. POF, independence, joint conditional-coverage LR tests with chi-squared p-values.
  Updated: 2026-05-12
- How to use Walk-Forward Validation Visualizer: https://aifinhub.io/calculator-guides/walk-forward-validation-visualizer/
  Description: Walk-Forward Validation Visualizer: returns CSV in. Per-window IS vs OOS Sharpe, IS-to-OOS drop, rolling and anchored modes — visual overfit check.
  Updated: 2026-05-12
- How to use Walk-Forward Validator: https://aifinhub.io/calculator-guides/walk-forward-validator/
  Description: Walk-Forward Validator: upload returns. Rolling or expanding IS-OOS windows. Per-window Sharpe, walk-forward efficiency, concatenated OOS equity curve.
  Updated: 2026-05-12

### Statistics (10)
- AI Agents and Automation in Markets Statistics: https://aifinhub.io/statistics/ai-agents-in-markets-statistics/
  Description: AI agents and automation in markets statistics: algorithmic execution share, electronic order flow, and regulator warnings on AI-driven volatility.
  Updated: 2026-05-26
- AI Fraud Detection in Finance Statistics: https://aifinhub.io/statistics/ai-fraud-detection-finance-statistics/
  Description: AI fraud detection statistics for payments and finance: fraud value blocked, detection-rate gains, false-positive reductions, reported as vendor claims.
  Updated: 2026-05-26
- AI Governance and Regulation in Finance Statistics: https://aifinhub.io/statistics/ai-governance-finance-regulation-statistics/
  Description: AI governance statistics for finance: EU AI Act timelines and fines, regulator-flagged risks, and the gap between AI adoption and formal strategy.
  Updated: 2026-05-26
- AI in Finance Adoption Statistics: https://aifinhub.io/statistics/ai-in-finance-adoption-statistics/
  Description: Sourced statistics on AI and generative-AI adoption across financial services: deployment rates, use cases, governance gaps, and where the money is going.
  Updated: 2026-05-26
- Generative AI Economic Value in Banking Statistics: https://aifinhub.io/statistics/generative-ai-banking-value-statistics/
  Description: Generative AI banking value statistics: McKinsey and Citi profit projections, top use cases, and where the estimated economic value concentrates.
  Updated: 2026-05-26
- Generative AI Spend in Financial Services Statistics: https://aifinhub.io/statistics/generative-ai-spend-financial-services-statistics/
  Description: Generative-AI spend statistics for financial services: AI budget share, ROI self-estimates, bank tech-budget figures, and production use-case counts.
  Updated: 2026-05-26
- LLM Accuracy on Financial Benchmarks Statistics: https://aifinhub.io/statistics/llm-financial-benchmark-accuracy-statistics/
  Description: LLM financial benchmark accuracy statistics: FinBen task results, sentiment accuracy versus FinBERT, and where models are strongest and weakest.
  Updated: 2026-05-26
- LLM Cost Trends for Finance Workloads Statistics: https://aifinhub.io/statistics/llm-cost-trends-finance-statistics/
  Description: LLM cost trends for finance workloads: sourced per-token price declines, fold reductions over time, and the drivers behind falling inference costs.
  Updated: 2026-05-26
- LLM Reliability in Finance Statistics: https://aifinhub.io/statistics/llm-reliability-in-finance-statistics/
  Description: Sourced statistics on large language model reliability for financial tasks: hallucination rates, numerical-reasoning accuracy, citation faithfulness, and benchmark gaps.
  Updated: 2026-05-26
- RAG vs Fine-Tuning Economics Statistics: https://aifinhub.io/statistics/rag-vs-fine-tuning-finance-statistics/
  Description: RAG vs fine-tuning economics statistics: sourced accuracy gains from each approach, whether they stack, and how grounding affects hallucination.
  Updated: 2026-05-26