Accuracy — gru_s3
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 | +0.0728 | 12.0 | +0.84% | 55.8% | 54.5% | 0.0356 | 5.804459 |
| +7d | 265 | 178k | +0.0862 | 14.6 | +1.95% | 60.7% | 61.1% | 0.0937 | 16.416426 |
| +30d | 265 | 177k | +0.1199 | 19.4 | +7.61% | 59.9% | 67.2% | 0.2086 | 32.847288 |
By month
| month | IC +1d | hit +1d | LS +1d | IC +7d | hit +7d | LS +7d | IC +30d | hit +30d | LS +30d | days |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-01 | +0.075 | 55.9% | +0.87% | +0.096 | 62.9% | +0.92% | +0.009 | 47.2% | -1.54% | 28 |
| 2025-12 | +0.038 | 56.5% | +1.05% | +0.052 | 60.2% | +3.25% | +0.071 | 61.7% | +5.47% | 31 |
| 2025-11 | +0.073 | 51.1% | +1.53% | +0.075 | 45.2% | +3.94% | +0.082 | 60.2% | +8.47% | 30 |
| 2025-10 | +0.059 | 59.2% | +0.62% | +0.050 | 65.6% | -0.01% | +0.156 | 46.1% | +14.68% | 31 |
| 2025-09 | +0.068 | 58.8% | +0.23% | +0.052 | 71.3% | +0.06% | +0.064 | 84.7% | +0.40% | 30 |
| 2025-08 | +0.074 | 49.8% | +0.47% | +0.071 | 49.8% | +1.24% | +0.124 | 58.3% | +7.51% | 31 |
| 2025-07 | +0.089 | 53.5% | +1.00% | +0.109 | 53.8% | +2.80% | +0.120 | 51.9% | +6.61% | 31 |
| 2025-06 | +0.078 | 59.4% | +0.74% | +0.086 | 72.3% | +0.72% | +0.170 | 61.9% | +9.20% | 30 |
| 2025-05 | +0.112 | 59.5% | +1.16% | +0.218 | 67.8% | +5.34% | +0.323 | 68.8% | +19.75% | 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.