Keresztvalidálás

Keresztvalidálás, known in English as cross-validation, is a resampling technique used to evaluate machine learning models on a limited data sample. It provides an estimate of how well the model will generalize to an independent dataset. The core idea is to split the available data into multiple subsets.

In the most common form, k-fold cross-validation, the data is randomly divided into k equal-sized folds. The model is then trained and evaluated k times. In each iteration, one fold is held out as the testing set, and the remaining k-1 folds are used for training. This process ensures that every data point gets to be in the testing set exactly once. The performance metric is then averaged across all k iterations to get a more robust estimate of the model's performance.

Another variant is leave-one-out cross-validation (LOOCV), which is an extreme case of k-fold cross-validation where k is equal to the number of data points. In LOOCV, the model is trained n times, where n is the total number of samples. In each iteration, one sample is used for testing, and the rest are used for training. While LOOCV provides a nearly unbiased estimate of the model's performance, it can be computationally very expensive.

Stratified cross-validation is used for classification tasks to ensure that each fold preserves the percentage of samples for each target class as in the complete set. This is particularly important when dealing with imbalanced datasets. Cross-validation helps in selecting the best performing model and tuning its hyperparameters, preventing overfitting to the training data.