Cross Validation


A validation method used in Supervised Learning to evaluate the generalization error using all available examples.

K-fold Cross Validation


The dataset is separated into k folds. For each of the k folds, the other k-1 folds are used to train the model, and the k fold is used for testing.

For Classification - 20230302070735 problems with unbalanced classes, a stratification step is added so that the fold has the same proportion of classes as the initial set.

META

Status:: #wiki/notes/mature
Plantations:: Machine Learning
References::