Menu
Login Get Started
All Sports Performance
AD TEST MODE
PERFORMANCE HEADER
Mock Placement 728x90
LI

Ligue 1

soccer • Performance Deep Dive

Trained Never Predicted Never
All-Time Average (158 folds)
Flat ROI
Hit Rate
Recent Trend (last 0 folds · Jan 16–Feb 20, 2026 )
Flat ROI
Hit Rate
Out-of-sample Accuracy
52.9%

Avg across 158 folds

AUC-ROC
0.506

0.5 = coin flip · 1.0 = perfect

Log Loss
0.8508

Lower is better

Brier Score
0.2949

Probability calibration

158 validation folds
Aug 18, 2018 – Feb 20, 2026

Final Holdout Test

Held back from all training and fold evaluation — the cleanest out-of-sample signal.

No holdout data available. Re-run prediction-system run --sport ligue1 to generate holdout metrics.

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter

Betting Simulation

Supporter+
Recommendation ROI
Recommendation Win Rate
Universe ROI
Universe Win Rate

Supporter access required

Unlock Supporter
Model: XGBoostModel
Calibration: platt
All-Time Average (122 folds)
Flat ROI
+27.6%
Hit Rate
34.3%
-18.1pp vs b/e
Recent Trend (last 3 folds · Feb 14–Apr 10, 2026 ) ↑ Improving
Flat ROI
+53.1%
+25.5pp vs avg
Hit Rate
38.7%
Out-of-sample Accuracy
43.1%

Avg across 122 folds

AUC-ROC
0.600

0.5 = coin flip · 1.0 = perfect

Log Loss
1.0741

Lower is better

Brier Score
N/A (multiclass)

Probability calibration

122 validation folds
Oct 14, 2017 – Apr 10, 2026

Final Holdout Test

Held back from all training and fold evaluation — the cleanest out-of-sample signal.

No holdout data available. Re-run prediction-system run --sport ligue1 to generate holdout metrics.

Fold-by-Fold Metrics

Supporter+ required

Supporter access required

Unlock fold-level charts to identify training stability.

Unlock Supporter

Betting Simulation

Supporter+
Recommendation ROI
Recommendation Win Rate
Universe ROI
Universe Win Rate

Supporter access required

Unlock Supporter
Model: CatBoostModel
Calibration: none (multiclass)