Skip to main content
aifinhub
Risk & Portfolio Construction Formula

Sortino Ratio Formula

The Sortino ratio divides a strategy's excess return over a target by its downside deviation, which measures only the volatility of returns below that target. Upside volatility does not count against the score, so a Sortino ratio rewards strategies whose dispersion is concentrated in good outcomes.

By AI Fin Hub Research · AI Fin Hub Team
Best Next MoveCalculators

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.

CalculatorOpen ->

On This Page

Formula

Copy the exact expression or work through it step by step below.

Sortino = (E[R_p] - T) / DD DD = sqrt( (1/n) x sum_over_R<T ( min(0, R_i - T) )^2 ) Annualized: Sortino_annual = Sortino_period x sqrt(N)

Variables

E[R_p]

Mean portfolio return

Arithmetic mean of the strategy's per-period return over the sample, expressed in the same frequency as the target.

T

Target return (MAR)

The minimum acceptable return per period below which a return is treated as a shortfall. Common choices are zero or the per-period risk-free rate. Returns at or above T contribute nothing to the denominator.

DD

Downside deviation

Root mean square of the negative deviations from the target. Importantly, the sum of squared shortfalls is divided by n, the total number of observations, not just the count of below-target periods. This keeps the measure comparable across samples with different shortfall frequencies.

n

Number of observations

Total count of return periods in the sample. The full count is used as the divisor inside the downside deviation, by Sortino and Price's original definition.

N

Periods per year

Annualization factor: 252 for daily, 52 for weekly, 12 for monthly returns. The ratio scales by the square root of N under the i.i.d. assumption, exactly as the Sharpe ratio does.

Step By Step

  1. 1

    Choose a target return T. Use zero for absolute downside risk, or the per-period risk-free rate to match a Sharpe comparison.

    Set T = 0 to penalize only periods where the strategy lost money.

  2. 2

    For each period, compute the shortfall: the return minus the target, but replace any non-negative result with zero so only below-target periods contribute.

    Returns of +3%, -2%, +1%, -4% against T = 0 give shortfalls of 0, -2%, 0, -4%.

  3. 3

    Square each shortfall, sum them, divide by the total number of observations n, then take the square root to get downside deviation.

    Squared shortfalls 0, 0.0004, 0, 0.0016 sum to 0.0020; divided by 4 is 0.0005; the square root is 0.02236, or 2.24%.

  4. 4

    Subtract the target from the mean return and divide by the downside deviation to get the per-period Sortino ratio.

    Mean return -0.5% over T = 0 divided by 2.24% gives -0.224 per period.

  5. 5

    Annualize by multiplying by the square root of the number of periods per year.

    A monthly Sortino of 0.30 annualizes to 0.30 x sqrt(12) = 1.04.

Worked Example

Trend strategy, four monthly returns, target T = 0

Monthly returns

+4%, -3%, +5%, -2%

Target T

0%

Periods per year

12

Mean return = (4 - 3 + 5 - 2)/4 = 1.0% = 0.01. Shortfalls below 0 are -0.03 and -0.02; squared they are 0.0009 and 0.0004, summing to 0.0013. Divide by n = 4: 0.000325. Downside deviation = sqrt(0.000325) = 0.01803 = 1.803%. Monthly Sortino = 0.01 / 0.01803 = 0.555. Annualized = 0.555 x sqrt(12) = 0.555 x 3.464 = 1.922.

Annualized Sortino of about 1.92. Because the two up months (+4%, +5%) are larger than the two down months, the downside deviation stays small relative to the mean, lifting the Sortino well above what a Sharpe ratio would report on the same series.

Common Variations

Sharpe ratio: divides by total standard deviation instead of downside deviation, so upside swings also lower the score.
Calmar ratio: replaces the volatility denominator entirely with maximum drawdown, focusing on the single worst peak-to-trough loss.
Omega ratio: uses the full distribution of gains over losses relative to a threshold rather than a single second-moment summary.
Some implementations divide the squared shortfalls by the count of below-target periods only; this departs from Sortino and Price's definition and inflates the ratio.

Try These Tools

Run the numbers next

Sources & References

Related Content

Keep the topic connected

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