Deep dive into model performance and calibration
Overall Accuracy
56.0%
79 / 141 correct
Total Predictions
141
Completed fights reviewed
High Confidence Accuracy
70.0%
Top tier predictions
High
68.4%
38 fights
Low
76.5%
17 fights
Medium
57.6%
33 fights
Uncertain
39.6%
53 fights
Accuracy shows how often the predicted winner won. Confidence tiers group predictions by calibrated probability. Higher confidence tiers should have higher accuracy.
| Tier | Total Fights | Correct | Accuracy | Avg Probability |
|---|---|---|---|---|
| High | 38 | 26 | 68.4% | 79.6% |
| Low | 17 | 13 | 76.5% | 65.0% |
| Medium | 33 | 19 | 57.6% | 65.2% |
| Uncertain | 53 | 21 | 39.6% | 54.7% |
| Version | Predictions | Correct | Accuracy |
|---|---|---|---|
| XGBoost (calibrated) | 141 | 79 | 56.0% |
Predicted probability vs actual win rate. Points on the diagonal indicate perfect calibration.
Calibration explained: The chart shows predicted probability (x-axis) vs actual win rate (y-axis). Points on the diagonal (45°) indicate perfect calibration - the predicted probabilities match observed outcomes. Points above the line indicate the model is overconfident. Points below indicate underconfidence.