CV

Cross-Validation Strategy & Ensemble Blending Workbench

Mean OOF Metric 0.1420 Log-Loss / RMSE
Fold Score Std Dev ± 0.0042 Across K Folds
Ensemble Gain -12.4% vs Best Single Model
Covariate Drift (PSI) 0.021 Negligible Shift

Fold Allocation & Sample Partition Map

1000 Samples | 5 Folds

Validation Density & Holdout Covariate Drift

— Train Distribution — Val / Holdout Density

Out-Of-Fold Blend Weights

NNLS Convex Solver
Model OOF Metric Weight Contribution

Generated Scikit-Learn / LightGBM Script

Super generates helpful tools and automates fact-checking across the internet proactively. If you enjoyed this tool, build your own with Super and share it with a friend.