Keresztvalidáció

Keresztvalidáció, in English cross-validation, is a resampling procedure used to evaluate machine learning models on a limited data sample. It helps in assessing how well a model generalizes to an independent dataset. The most common form is k-fold cross-validation. In k-fold cross-validation, the original data is randomly partitioned into k equal-sized subsets, called folds. The model is then trained k times. Each time, one of the k folds is used as the test set, and the remaining k-1 folds are used as the training set. The performance metrics from these k runs are then averaged to provide an estimate of the model's performance on unseen data.

This method is crucial for preventing overfitting, a phenomenon where a model learns the training data too well, including its noise, and performs poorly on new data. By systematically holding out different parts of the data for testing, cross-validation provides a more robust estimate of the model's predictive accuracy than a single train-test split. The choice of k is a hyperparameter; common values include 5 or 10. A higher k generally leads to a more reliable estimate but increases computation time. Leave-one-out cross-validation is an extreme case where k equals the number of data points, meaning the model is trained N-1 times for a dataset of size N.