Setup Score Backtest
What does setup score actually predict?
Forward T+10/T+30/T+60 returns for every historical Stage 2 row, bucketed by setup_score band and entry regime. Every number is computed from real OHLCV — no model assumptions.
357,743 samples2024-01-01 → 2026-05-25Window: T+10 / T+30 / T+60 trading days
By setup score band
Mean / median forward return + win rate (% positive). Higher bands should produce higher means + higher win rates.
Swipe for full table →
| Band | Samples | Mean return % | Median return % | Win rate % |
|---|
| T+10 | T+30 | T+60 | T+10 | T+30 | T+60 | T+10 | T+30 | T+60 |
|---|
| under-4 | 38,192 | -0.52% | -0.99% | -1.68% | -1.22% | -2.77% | -5.13% | 42.6% | 40.0% | 37.8% |
| 4-5 | 52,902 | -0.33% | -0.80% | -0.07% | -1.12% | -2.60% | -3.91% | 43.0% | 40.7% | 40.3% |
| 5-6 | 79,608 | +0.26% | +0.52% | +1.03% | -0.60% | -1.54% | -2.47% | 46.1% | 44.7% | 43.7% |
| 6-7 | 83,936 | +0.51% | +1.10% | +1.89% | -0.36% | -0.87% | -1.65% | 47.6% | 47.0% | 46.4% |
| 7-8 | 72,994 | +0.72% | +1.68% | +2.85% | -0.19% | -0.14% | -0.51% | 48.6% | 49.5% | 48.9% |
| 8-9 | 27,984 | +1.18% | +2.20% | +4.41% | -0.04% | +0.05% | +0.49% | 49.8% | 50.1% | 51.0% |
| 9-10 | 2,127 | +1.73% | +0.65% | +2.93% | -0.19% | -0.63% | -1.67% | 48.8% | 48.1% | 47.4% |
Color: green = better, red = worse. Win rate >50% means more setups in the band closed up than down at that horizon.
Regime × Score win-rate matrix
T+30 win rate (% positive) for each combination of market regime and setup score band. Higher cells = better historical odds. Hover for sample size.
Swipe for full table →
| Regime ↓ / Score → | under-4 | 4-5 | 5-6 | 6-7 | 7-8 | 8-9 | 9-10 |
|---|
| BULL | 38% n=8,466 | 41% n=16,827 | 45% n=31,291 | 48% n=31,770 | 51% n=24,975 | 51% n=10,115 | 52% n=608 |
| NEUTRAL_UP | 33% n=3,457 | 31% n=9,149 | 33% n=10,354 | 36% n=12,075 | 41% n=13,321 | 44% n=8,670 | 42% n=726 |
| TURNING | 64% n=215 | 64% n=850 | 66% n=1,634 | 57% n=2,702 | 66% n=3,818 | 66% n=3,006 | 59% n=375 |
| NEUTRAL_DOWN | 35% n=14,123 | 38% n=13,405 | 44% n=20,162 | 47% n=21,399 | 52% n=17,818 | 56% n=3,795 | 55% n=157 |
| CAUTION | 53% n=9,014 | 51% n=8,794 | 53% n=10,142 | 51% n=7,105 | 54% n=4,096 | 56% n=399 | — |
| BEAR | 38% n=2,917 | 43% n=3,877 | 51% n=6,025 | 53% n=8,885 | 49% n=8,966 | 45% n=1,999 | 40% n=261 |
Win rate<40%40-5050-6060-70>70%Hover any cell for sample size + avg return.
Method: for every (stock, date) where setup_score was computed since 2024-01-01, we took the close price on that date and the close at +10/+30/+60 trading days. The forward return is `(close_t / close_0 - 1) × 100`. The regime is `state_5` from `market_analytics` on the entry date. Past performance does not guarantee future results — use these numbers as a calibration of the score's signal quality, not as a forecast.