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
32
Win rate
28.13%
Median return
-3.59%
Median excess
-1.67%
Median MFE
+1.89%
Median MAE
-6.21%
Cohort drawdown
-11.82%
Evidence
30+ sample
8 Sept 2026 to 11 Sept 2026Regime benchmark: Nifty 500
| Market cap | Sample | Win rate | Median return | Median excess | MFE | MAE | Drawdown | Evidence |
|---|---|---|---|---|---|---|---|---|
| Large | 17 | 29.41% | -1.66% | -0.39% | +1.86% | -5.99% | -6.92% | Early |
| Small | 11 | 18.18% | -7.05% | -5.27% | +1.92% | -8.65% | -23.24% | Early |
| Mid | 4 | 50.00% | -1.31% | +0.27% | +2.27% | -4.49% | -11.77% | 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.