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 · sport=nba
| Predicted-prob bucket | N | Mean predicted | Actual win rate | Gap (actual − predicted) | Brier |
|---|---|---|---|---|---|
| <50% | 11 | 49.8% | 63.6% | +13.8pp | 0.249 |
| 50-55% | 113 | 51.7% | 54.0% | +2.3pp | 0.248 |
| 55-60% | 15 | 57.2% | 60.0% | +2.8pp | 0.245 |
| 60-65% | 6 | 61.6% | 83.3% | +21.7pp | 0.182 |
| 65-70% | 4 | 68.1% | 25.0% | -43.1pp | 0.368 |
| 70-75% | 7 | 72.8% | 85.7% | +12.9pp | 0.135 |
| 75-80% | 4 | 76.4% | 100.0% | +23.6pp | 0.056 |
| 80-90% | 6 | 84.4% | 100.0% | +15.6pp | 0.025 |