Accuracy — gru_s1
validation only · 2.3M
Summary
| horizon | days | token-days | rank IC | t | LS decile | hit (alpha) | hit (price) | MAE (alpha) | MAE (price) |
|---|---|---|---|---|---|---|---|---|---|
| +1d | 265 | 179k | +0.0768 | 13.6 | +0.96% | 55.7% | 54.4% | 0.0356 | 5.738361 |
| +7d | 265 | 178k | +0.0954 | 17.5 | +2.94% | 60.6% | 60.8% | 0.0934 | 16.139309 |
| +30d | 265 | 177k | +0.1186 | 21.0 | +9.39% | 60.3% | 68.0% | 0.2084 | 34.401386 |
By month
| month | IC +1d | hit +1d | LS +1d | IC +7d | hit +7d | LS +7d | IC +30d | hit +30d | LS +30d | days |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-01 | +0.073 | 56.2% | +0.80% | +0.091 | 63.1% | +0.68% | +0.026 | 47.0% | +4.82% | 28 |
| 2025-12 | +0.045 | 55.3% | +1.10% | +0.062 | 57.7% | +3.73% | +0.051 | 61.6% | +6.88% | 31 |
| 2025-11 | +0.086 | 51.1% | +1.73% | +0.094 | 44.1% | +5.35% | +0.103 | 59.2% | +7.96% | 30 |
| 2025-10 | +0.067 | 59.1% | +0.95% | +0.057 | 65.7% | +0.20% | +0.136 | 46.0% | +14.77% | 31 |
| 2025-09 | +0.060 | 58.9% | +0.31% | +0.057 | 71.3% | +1.84% | +0.062 | 84.8% | +4.12% | 30 |
| 2025-08 | +0.077 | 49.9% | +0.43% | +0.077 | 49.4% | +1.93% | +0.106 | 58.0% | +4.48% | 31 |
| 2025-07 | +0.099 | 53.5% | +0.95% | +0.119 | 53.8% | +3.82% | +0.151 | 52.2% | +9.92% | 31 |
| 2025-06 | +0.089 | 59.8% | +0.98% | +0.123 | 74.1% | +2.63% | +0.176 | 64.2% | +12.11% | 30 |
| 2025-05 | +0.102 | 58.8% | +1.47% | +0.204 | 68.3% | +7.23% | +0.292 | 72.7% | +22.15% | 23 |
t-stats at +7d and +30d are optimistic: consecutive windows overlap, so the effective sample size is closer to the number of distinct days than the number of rows. +1d is the clean read. Long-short spreads are before trading costs and slippage, and the tail of the top-1000 by volume is thin.