Sortino ratio
The Sortino ratio measures return per unit of risk, like the Sharpe ratio, but counting only downside volatility in the denominator. It starts from a sensible objection to Sharpe: penalising sharp gains as if they were risk does not match what actually worries an investor. It usually produces higher figures than Sharpe for the same portfolio, so comparing the two means nothing; only Sortino against Sortino makes sense.
How it is calculated
Sortino = (portfolio return − target return) ÷ downside deviation. It is Sharpe with one correction: the denominator holds not the whole volatility but only that of the periods which fell below the target. A portfolio returning 12 % with a 2 % target and 8 % downside deviation has a Sortino of 1.25. If its total volatility were 14 %, its Sharpe would be 0.71. The gap between the two numbers measures how much of its variability was upward: the further Sortino sits above Sharpe, the more the portfolio's asymmetry has been in your favour.
The figures in the example are invented and rounded so the arithmetic can be redone by hand. They are not data from any real company.
What it is NOT
It does not measure the probability of losing nor how much you can lose: VaR, CVaR and maximum drawdown are for that. And it is not comparable between portfolios using different targets —moving the target from 0 % to 2 % changes the number—, so it is worth stating which was used. It also shares the weakness of every ratio of this kind: it is computed on the past, and a strategy that has not had drawdowns yet has a magnificent Sortino right up to the day it does.
Formula
Sortino = (rentabilidad − tasa libre de riesgo) ÷ desviación a la baja See also
See it on real data
Celsmar computes this from the accounts companies file with their regulator, and shows which line every figure comes from. Free to start, no card.
Definition for informational purposes. It is not financial advice nor a recommendation to buy or sell.