K-fold cross-validation Machine Learning
noun phrase
Definition: A resampling-based validation procedure used to estimate how well a supervised learning model generalizes to unseen data by partitioning a dataset into k approximately equal folds, training the model on k−1 folds, and evaluating it on the remaining fold, repeated k times [Chen et al. 2025].
Example in context: “Additionally, to prevent overfitting and enhance model generalization ability, we implemented rigorous 10-fold cross-validation for each model.” [Xu et al. 2025]
Synonyms: k-fold CV; k-fold validation
Related terms: model validation; generalization; unseen data; holdout set; stratified k-fold cross-validation; cross-validation error