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% | 2088 | 41.6% | 39.4% | -2.3pp | 0.230 |
| 50-55% | 2702 | 52.0% | 51.0% | -1.0pp | 0.249 |
| 55-60% | 1538 | 57.4% | 56.0% | -1.4pp | 0.246 |
| 60-65% | 694 | 62.1% | 61.0% | -1.2pp | 0.238 |
| 65-70% | 532 | 67.2% | 60.5% | -6.7pp | 0.243 |
| 70-75% | 201 | 72.3% | 72.6% | +0.4pp | 0.197 |
| 75-80% | 378 | 76.6% | 75.1% | -1.5pp | 0.188 |
| 80-90% | 252 | 85.1% | 86.5% | +1.4pp | 0.114 |
| 90%+ | 167 | 93.8% | 94.6% | +0.8pp | 0.050 |