Skip to main content
aifinhub

Transparency

Methodology

Every tool, benchmark, and quantitative article publishes its methodology. Assumptions, formulas, data sources, limitations, changelog — all open, all reproducible.

How we work

Open methodology, named limits

Source hierarchy. Peer-reviewed research and official exchange / regulator documentation come first. Vendor whitepapers and named-author technical writing come next, used for product behaviour they themselves authored. Public benchmark datasets (HumanEval, GSM8K, BIG-Bench, etc.) are cited where the benchmark's own publication is the primary source. Our own measurements come last and are flagged as such — never blended into a claim that reads as third-party evidence.

Open methodology, named limits. Every tool's formulas, coefficients, and modelling choices are published on its methodology page, dated, and linked from the tool itself. Where a formula has a domain of applicability — Kelly assumes stationary edge, Black-Scholes assumes log-normal returns, Sharpe ignores tail risk — the page says so before it shows the number.

Reproducibility. Tools run client-side. Given the same inputs you provide, the same numbers come out — there is no server-side weighting, no vendor-supplied parameter we hide, no opaque model. Methodology pages document the formulas in enough detail to recompute results in a spreadsheet or notebook.

Update cadence. Vendor pricing and rate-card data are refreshed on a quarterly cycle, with the last-refreshed date stamped on the page. Formula derivations are dated at first publication and re-dated whenever the derivation or coefficients change. Material changes are listed in the changelog section of each methodology page.

Corrections. When we get a number wrong we fix it inline, bump the article's Last updated timestamp, and log a dated entry at /corrections/. Material corrections carry a banner on the affected page for 30 days. Full editorial policy at /editorial-standards/.

Every page contains

Scope

What the tool / benchmark measures — and what it does not.

Algorithm

Formulas or procedures with primary-source citations.

Assumptions

Explicit list of every modeling choice.

Data sources

Primary sources, retrieval dates, licensing.

Reproducibility

Steps to run the same calculation on other data.

Limitations

Documented weaknesses, edge cases, caveats.

References

Peer-reviewed papers and authoritative texts.

Changelog

Dated history of methodology changes.

Calculators

Formulas, moments, closed-form solutions · 16 pages

Fractional Kelly Sizer

Map conviction tiers to fractional Kelly bet sizes with a drawdown Monte Carlo simulator. Client-side. Private by default.

Calculators Open

Backtest Overfitting Score

Upload a backtest trade log and compute Probability of Backtest Overfitting (PBO), Deflated Sharpe Ratio, and the odds your edge survives live trading.

Calculators Open

Token-Cost Optimizer

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.

Calculators Open

Risk-Adjusted Returns Calculator

Paste a returns CSV. Sharpe, Sortino, Calmar, Omega, alpha, beta, tracking error, information ratio, max drawdown, and tail moments — plus.

Calculators Open

Correlation Matrix Visualizer

Paste a multi-asset returns CSV. See the Pearson correlation heatmap, condition number, average absolute correlation, and eigenvalue concentration.

Calculators Open

Returns Distribution Analyzer

Paste a returns CSV. Histogram, normal-overlay, QQ plot, skewness, excess kurtosis, Jarque-Bera test, tail-weight index. See why Sharpe alone misleads.

Calculators Open

Efficient Frontier Builder

Paste a multi-asset returns CSV. See the Markowitz mean-variance frontier, the minimum-variance portfolio, the max-Sharpe (tangency) portfolio.

Calculators Open

Financial Document Token Estimator

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.

Calculators Open

Agent Cost Envelope Calculator

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.

Calculators Open

Batch vs Real-Time Cost Calculator

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.

Calculators Open

Deflated Sharpe Ratio Calculator

Bailey & López de Prado deflated Sharpe — corrects observed Sharpe for selection bias across K trials. Reports deflated Sharpe, PSR (probability of skill).

Calculators Open

Earnings-Call Summarization Cost Calculator

LLM cost per stock per quarter to summarize earnings transcripts across Sonnet, Opus, GPT-5.5, Gemini 2.5 Pro/Flash. Cache-hit-rate aware. Snapshot pricing.

Calculators Open

Sharpe vs Sortino Calculator

Paste daily returns; get Sharpe, Sortino, Calmar, and Omega side-by-side with a recommendation on which ratio fits your distribution.

Calculators Open

Statistical Arbitrage Capacity Calculator

Maximum strategy AUM from signal half-life, daily volume, slippage, fees, and target Sharpe. Square-root impact closed-form.

Calculators Open

Position Sizing under Edge Variance

Bayesian-Kelly bet sizing when your edge is itself uncertain. Compare deterministic Kelly, Bayesian-adjusted, and conservative lower-bound versions.

Calculators Open

Drawdown-Recovery Markov Simulator

Time to recover from an N% drawdown given monthly Sharpe + skew + kurtosis. Cornish-Fisher Monte Carlo, percentile distribution of recovery months.

Calculators Open

Comparators

Ranking methodology + scoring rules · 5 pages

Playgrounds

Algorithms, heuristics, attack corpora · 19 pages

Agent Skill Tester for Markets

Paste a SKILL.md definition + sample input + your Anthropic API key. See structured extraction, token cost, and latency — all in your browser. No signup.

Playgrounds Open

Prompt Regression Tester

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.

Playgrounds Open

Hallucination Detector

Paste a source document + an LLM's extraction. Every numeric claim in the output is checked against the source. Client-side. Catches silent fabrication.

Playgrounds Open

Order Book Replay Visualizer

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.

Playgrounds Open

Calibration Dojo

Train your probabilistic intuition. Answer binary forecasting questions at any confidence level; track Brier score and reliability curve over time. All.

Playgrounds Open

Walk-Forward Validator

Upload a returns CSV. Rolling or expanding IS/OOS windows, per-window Sharpe, walk-forward efficiency, and a concatenated OOS equity curve. Catches regime.

Playgrounds Open

Options Greeks Explorer

Black-Scholes pricer + live Greeks visualizer. Drag spot, strike, vol, DTE, rate, dividend yield — see delta, gamma, theta, vega, rho update.

Playgrounds Open

Price-Blind Research Auditor

Paste a research prompt or agent context bundle. The auditor flags price numbers, directional words, and outcome-leaking phrases that cause LLMs.

Playgrounds Open

Prompt Injection Tester

Red-team a finance agent against 24 documented prompt-injection attacks — direct override, role confusion, indirect injection via retrieved content.

Playgrounds Open

Options Payoff Builder

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.

Playgrounds Open

Pair Trading Cointegration Tester

Paste two price series. Engle-Granger cointegration test: OLS hedge ratio, Augmented Dickey-Fuller on residuals, Ornstein-Uhlenbeck half-life, z-score.

Playgrounds Open

Execution Simulator

Model realistic order fills — square-root market impact, linear temporary impact, latency jitter, partial fills, and queue position. See the real cost.

Playgrounds Open

Structured Schema Validator for Finance

Paste LLM JSON output and validate against four pre-built finance schemas — research output, trade decision, risk snapshot, peer comparison — with sanity.

Playgrounds Open

Fallback Chain Simulator

Define a provider fallback chain, simulate rate-limit and latency failures, and see p50/p95/p99 latency, success rate, total cost, and degradation-event.

Playgrounds Open

Forecast Scoring Sandbox

Paste a forecast stream (probability + outcome) and see Brier score with full decomposition, log loss, reliability diagram, and bootstrap confidence.

Playgrounds Open

Walk-Forward Validation Visualizer

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.

Playgrounds Open

Cointegration Half-Life Solver

Engle-Granger residual ADF + Ornstein-Uhlenbeck half-life from any two price/return series. Hedge ratio, p-value, spread chart. Browser-only.

Playgrounds Open

VaR Backtest — Kupiec & Christoffersen

Paste P&L + VaR series and run Kupiec POF, Christoffersen independence, and joint conditional-coverage tests. Likelihood-ratio χ² p-values.

Playgrounds Open

LLM Finance Error Taxonomy

12 documented LLM-on-finance failure modes (hallucinated ticker, stale price, units, currency, off-by-100, fictional source, more). Paste output, see flags.

Playgrounds Open

Generators

Schema contracts + assumption lists · 4 pages

Directories

Curation criteria + scoring scales · 1 page

Planning estimates only — not financial, tax, or investment advice.