Superseded (2026-05-25) — this operator is a Layer-1 transform, not a Layer-0 atomic input. Merged into sortino_ratio_v1. Kept for history.

What (One-liner)

Sortino ratio — risk-adjusted return that only penalizes downside volatility. Asymmetric correction of Sharpe. Library-level primitive, candidate Canvas node.

How to use

from services.algo.time_series import sortino_ratio
sortino = sortino_ratio(returns, risk_free_rate=0.02)

Core formulas

excess = returns - rf/252
downside = [x for x in excess if x < 0]
sortino = mean(excess) / std(downside, ddof=0) × √252

Zero downside → 0.0.

Assumptions & applicability

Assumptions: Daily frequency + 252 annualization + MAR=0 (not custom target).

Applicability: Fat-tailed / skewed / hedge fund-style strategies.

Out of scope: Intraday, all-positive return sequences, n<30.

Known limitations

1. MAR hardcoded 0 (custom target return not supported)
2. Zero downside clamp 0 (BUG-GOLDEN-001 fix approach)
3. Shares annualization factor assumptions with Sharpe

References

Sortino & Price (1994) + Rollinger-Hoffman (2013) calculation pitfalls guide.

Golden Test

tests/golden/fixtures/tier1/sortino_ratio/, 1e-12 tolerance, 2026-04-20 passing.

Changelog

• 1.0.0 (2026-04-20) — First Active, BUG-GOLDEN-001 fix