Cross-validation

Berrar, Daniel (2025). Cross-validation. In: Ranganathan, Shoba; Cannataro, Mario and Khan, Mohammad Asif eds. Encyclopedia of Bioinformatics and Computational Biology, 2nd edition. Elsevier (In Press).

Abstract

Cross-validation is one of the most widely used data resampling methods for model selection and evaluation. Cross-validation can be used to tune the hyperparameters of statistical and machine learning models, to prevent overfitting, to compare learning algorithms, and to estimate the generalization error of predictive models. This article gives an introduction to the most common types of cross-validation, such as k-fold cross-validation, nested cross-validation, and leave-one-out cross-validation, as well as their relation to other data resampling strategies.

Viewing alternatives

Item Actions

Export

You can export this page using these formats