Cross-Validation

A single train/test split can be lucky or unlucky. Cross-validation gives a more reliable estimate.

K-Fold Cross-Validation

Why Cross-Validation?

Cross-Validation in Sklearn

Key Takeaways

• K-Fold CV splits data into K parts, trains K times
• Each sample is used for testing exactly once
• More reliable than single train/test split
• Use K=5 or K=10 for most cases
• Report mean ± std of CV scores
• Essential for comparing models and hyperparameter tuning