UFC / MMA
combat • Performance Deep Dive
Avg across 153 folds
0.5 = coin flip · 1.0 = perfect
Lower is better
Probability calibration
Final Holdout Test
Held back from all training and fold evaluation — the cleanest out-of-sample signal.
prediction-system run --sport ufc
to generate holdout metrics.
Fold-by-Fold Metrics
Supporter+ requiredBetting Simulation
Supporter+Supporter access required
Unlock SupporterAvg across 153 folds
0.5 = coin flip · 1.0 = perfect
Lower is better
Probability calibration
Final Holdout Test
Held back from all training and fold evaluation — the cleanest out-of-sample signal.
prediction-system run --sport ufc
to generate holdout metrics.
Fold-by-Fold Metrics
Supporter+ requiredBetting Simulation
Supporter+Supporter access required
Unlock SupporterAvg across 153 folds
0.5 = coin flip · 1.0 = perfect
Lower is better
Probability calibration
Final Holdout Test
Held back from all training and fold evaluation — the cleanest out-of-sample signal.
prediction-system run --sport ufc
to generate holdout metrics.
Fold-by-Fold Metrics
Supporter+ requiredBetting Simulation
Supporter+Supporter access required
Unlock SupporterNo backtest data yet
The model hasn't been run for this market yet. Data will appear here once the pipeline has been executed.
Avg across 152 folds
0.5 = coin flip · 1.0 = perfect
Lower is better
Probability calibration
Final Holdout Test
Held back from all training and fold evaluation — the cleanest out-of-sample signal.
prediction-system run --sport ufc
to generate holdout metrics.
Fold-by-Fold Metrics
Supporter+ requiredBetting Simulation
Supporter+Supporter access required
Unlock Supporter