Accuracy — gru_s4
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 | +0.0679 | 11.8 | +0.88% | 53.8% | 52.6% | 0.0357 | 5.696285 |
| +7d | 265 | 178k | +0.0865 | 15.7 | +2.67% | 59.4% | 59.0% | 0.0940 | 16.297232 |
| +30d | 265 | 177k | +0.1184 | 18.3 | +9.57% | 58.3% | 64.9% | 0.2099 | 33.708964 |
By month
| month | IC +1d | hit +1d | LS +1d | IC +7d | hit +7d | LS +7d | IC +30d | hit +30d | LS +30d | days |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-01 | +0.068 | 56.1% | +0.71% | +0.072 | 62.9% | +0.20% | -0.007 | 46.8% | +5.99% | 28 |
| 2025-12 | +0.037 | 48.9% | +1.05% | +0.056 | 53.2% | +4.09% | +0.052 | 55.0% | +4.20% | 31 |
| 2025-11 | +0.071 | 52.1% | +1.71% | +0.095 | 44.0% | +4.36% | +0.108 | 49.8% | +13.31% | 30 |
| 2025-10 | +0.054 | 53.6% | +0.57% | +0.057 | 65.0% | +0.77% | +0.176 | 49.6% | +19.19% | 31 |
| 2025-09 | +0.064 | 58.1% | +0.52% | +0.055 | 71.2% | +2.35% | +0.049 | 84.6% | +4.46% | 30 |
| 2025-08 | +0.059 | 49.4% | +0.41% | +0.079 | 49.2% | +1.77% | +0.134 | 57.9% | +6.87% | 31 |
| 2025-07 | +0.089 | 53.4% | +1.02% | +0.113 | 53.7% | +3.88% | +0.136 | 51.1% | +8.23% | 31 |
| 2025-06 | +0.076 | 57.9% | +0.72% | +0.088 | 71.6% | +0.88% | +0.151 | 62.4% | +5.16% | 30 |
| 2025-05 | +0.102 | 55.1% | +1.31% | +0.190 | 66.3% | +6.47% | +0.300 | 70.5% | +21.24% | 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.