Accuracy — beta_5y
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 | +0.0830 | 13.8 | +0.92% | 56.0% | 54.2% | 0.0355 | 5.831601 |
| +7d | 265 | 178k | +0.1056 | 17.9 | +2.92% | 61.3% | 61.0% | 0.0932 | 16.331124 |
| +30d | 265 | 177k | +0.1209 | 20.0 | +9.38% | 60.6% | 68.3% | 0.2081 | 32.855650 |
By month
| month | IC +1d | hit +1d | LS +1d | IC +7d | hit +7d | LS +7d | IC +30d | hit +30d | LS +30d | days |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-01 | +0.078 | 56.0% | +0.64% | +0.094 | 63.1% | +1.43% | +0.021 | 47.5% | +10.02% | 28 |
| 2025-12 | +0.049 | 56.7% | +0.88% | +0.059 | 59.8% | +3.37% | +0.058 | 61.7% | +5.92% | 31 |
| 2025-11 | +0.100 | 51.7% | +1.86% | +0.132 | 47.3% | +7.90% | +0.115 | 62.7% | +14.32% | 30 |
| 2025-10 | +0.076 | 59.2% | +0.66% | +0.073 | 65.8% | +0.82% | +0.155 | 44.7% | +16.11% | 31 |
| 2025-09 | +0.070 | 58.8% | +0.46% | +0.058 | 71.3% | +0.79% | +0.072 | 84.8% | +0.90% | 30 |
| 2025-08 | +0.086 | 49.8% | +0.56% | +0.092 | 49.3% | +1.43% | +0.125 | 58.0% | +8.07% | 31 |
| 2025-07 | +0.101 | 53.4% | +0.94% | +0.099 | 53.6% | +1.52% | +0.104 | 51.3% | +3.26% | 31 |
| 2025-06 | +0.087 | 59.8% | +1.05% | +0.152 | 74.2% | +3.76% | +0.166 | 63.5% | +7.53% | 30 |
| 2025-05 | +0.105 | 59.6% | +1.33% | +0.221 | 69.5% | +5.99% | +0.311 | 74.9% | +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.