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=3,584TENNIS_WTA N=909TENNIS_ATP N=873MMA_MIXED_MARTIAL_ARTS N=388NFL_PRESEASON N=145LALIGA N=116NCAAF N=95SERIEA N=87EPL N=86LIGUE1 N=84UCL N=61BUNDESLIGA N=53NBA N=12NCAAB N=11NHL N=9AMERICANFOOTBALL_NFL N=2

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=tennis_atp

Overall: N = 873 · mean predicted 64.2% · actual win rate 67.0% · gap +2.8pp · Brier 0.216 · log-loss 0.622
Calibration by predicted-probability bucket.
Predicted-prob bucket N Mean predicted Actual win rate Gap (actual − predicted) Brier
50-55% 173 52.3% 60.1% +7.8pp 0.247
55-60% 226 57.6% 60.2% +2.6pp 0.241
60-65% 97 61.4% 59.8% -1.6pp 0.240
65-70% 130 67.6% 76.9% +9.4pp 0.186
70-75% 78 71.7% 65.4% -6.3pp 0.228
75-80% 115 77.3% 77.4% +0.1pp 0.176
80-90% 28 84.4% 85.7% +1.3pp 0.122
90%+ 26 93.8% 88.5% -5.3pp 0.103