For every bucket of predicted probability, what did the model actually hit? A well-calibrated model has actual win rate ≈ predicted prob. A negative gap means the model is overconfident in that bucket (dangerous); positive gap means it's underpredicting (safe). Rows turn red when |gap| > 5pp AND N ≥ 10.
Combined "all sports" is rarely meaningful — sports differ in market efficiency, signal availability, and base rates. Use the chips to drill into a single sport. N<50 (red) means the calibration is brittle; N≥200 (green) is trustworthy.
Filter: window=90d
| Predicted-prob bucket | N | Mean predicted | Actual win rate | Gap (actual − predicted) | Brier |
|---|---|---|---|---|---|
| <50% | 1917 | 41.8% | 39.6% | -2.2pp | 0.232 |
| 50-55% | 2485 | 52.1% | 51.0% | -1.0pp | 0.249 |
| 55-60% | 1562 | 57.4% | 55.6% | -1.8pp | 0.247 |
| 60-65% | 690 | 62.1% | 59.7% | -2.4pp | 0.241 |
| 65-70% | 529 | 67.2% | 61.1% | -6.2pp | 0.241 |
| 70-75% | 196 | 72.2% | 74.0% | +1.8pp | 0.191 |
| 75-80% | 375 | 76.6% | 74.4% | -2.2pp | 0.192 |
| 80-90% | 223 | 85.3% | 86.5% | +1.2pp | 0.114 |
| 90%+ | 169 | 93.8% | 94.7% | +0.9pp | 0.049 |