Model calibration audit

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.

Calibration cohort by sport (click to filter):
All sports MLB N=3,353TENNIS_WTA N=753TENNIS_ATP N=748MMA_MIXED_MARTIAL_ARTS N=407LIGUE1 N=89NFL_PRESEASON N=65NBA N=42NHL N=33LALIGA N=26SERIEA N=19EPL N=15UCL N=13NCAAB N=11CRICKET_IPL N=6BUNDESLIGA N=3

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

Overall: N = 407 · mean predicted 59.2% · actual win rate 59.5% · gap +0.2pp · Brier 0.211 · log-loss 0.611
Calibration by predicted-probability bucket.
Predicted-prob bucket N Mean predicted Actual win rate Gap (actual − predicted) Brier
<50% 89 40.8% 36.0% -4.9pp 0.217
50-55% 75 52.7% 57.3% +4.6pp 0.246
55-60% 47 57.8% 44.7% -13.1pp 0.257
60-65% 60 61.6% 60.0% -1.6pp 0.242
65-70% 55 67.1% 74.5% +7.4pp 0.193
70-75% 30 71.9% 86.7% +14.8pp 0.140
75-80% 20 77.2% 75.0% -2.2pp 0.189
80-90% 19 83.2% 89.5% +6.3pp 0.101
90%+ 12 93.8% 91.7% -2.1pp 0.082