Evidence by cohort
Signal performance laboratory
Fixed-horizon outcomes grouped without removing failures. Medians reduce outlier distortion; MAE and drawdown expose risk that a headline win rate can hide.
Signal set
Sample
240
Win rate
39.58%
Median return
-0.56%
Median excess
-0.40%
Median MFE
+1.47%
Median MAE
-1.85%
Cohort drawdown
-18.07%
Evidence
30+ sample
8 Sept 2026 to 19 Oct 2026Regime benchmark: Nifty 500
| Setup | Sample | Win rate | Median return | Median excess | MFE | MAE | Drawdown | Evidence |
|---|---|---|---|---|---|---|---|---|
| Double Bottom Base | 68 | 36.76% | -0.64% | -0.59% | +1.76% | -2.10% | -25.23% | 30+ sample |
| Bullish Engulfing | 50 | 34.00% | -1.27% | -1.00% | +1.44% | -2.47% | -20.76% | 30+ sample |
| Ascending Triangle | 48 | 37.50% | -0.66% | +0.04% | +1.35% | -1.99% | -8.69% | 30+ sample |
| Morning Star | 43 | 48.84% | -0.28% | -0.28% | +1.39% | -1.60% | -8.06% | 30+ sample |
| Rounded Bottom | 13 | 46.15% | -0.23% | -0.23% | +1.05% | -1.37% | -7.15% | Early |
| Cup With Handle | 11 | 45.45% | -0.21% | +1.41% | +1.67% | -1.61% | -5.91% | Early |
| Bull Flag | 3 | 0.00% | -2.37% | -2.37% | +0.46% | -2.89% | -7.09% | Under 10 |
| Hammer | 2 | 100.00% | +5.00% | +5.00% | +5.00% | -1.83% | 0.00% | Under 10 |
| Piercing Pattern | 2 | 50.00% | -1.21% | -1.33% | +1.64% | -2.34% | -2.56% | Under 10 |
Returns: Median is used for return, excess return, MFE, and MAE to reduce outlier distortion. Return greater than 0% at the selected fixed horizon.
Drawdown: Signals from the same publication date are equal-weighted as one cohort, then cohort returns are compounded chronologically.
Market regime: Bullish, bearish, or sideways uses the benchmark close versus its trailing 50-session average and trailing 20-session return, using only data available by publication day.
Sample discipline: Groups below 10 outcomes are insufficient; 10-29 are early evidence; 30 or more are established samples, not proof of future performance.