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=mma_mixed_martial_arts
| Predicted-prob bucket | N | Mean predicted | Actual win rate | Gap (actual − predicted) | Brier |
|---|---|---|---|---|---|
| <50% | 140 | 39.9% | 34.3% | -5.6pp | 0.226 |
| 50-55% | 78 | 52.4% | 61.5% | +9.2pp | 0.243 |
| 55-60% | 59 | 57.7% | 57.6% | -0.1pp | 0.242 |
| 60-65% | 74 | 62.1% | 62.2% | +0.0pp | 0.239 |
| 65-70% | 58 | 67.0% | 70.7% | +3.7pp | 0.207 |
| 70-75% | 32 | 72.3% | 71.9% | -0.4pp | 0.207 |
| 75-80% | 39 | 77.1% | 74.4% | -2.8pp | 0.191 |
| 80-90% | 40 | 83.1% | 77.5% | -5.6pp | 0.178 |
| 90%+ | 6 | 94.2% | 83.3% | -10.9pp | 0.144 |