Cross-validation is a method of validating a hypothesis about data. At the beginning of the analysis process, the data is split into learning data and testing data. A hypothesis is fit to the learning data, and then its actual error is measured on the testing data. This way, we can estimate how well a hypothesis may perform on future data. Reducing the amount of learning data can also be beneficial as it reduces the chance of hypothesis over-fitting. This is where a hypothesis is trained to a particularly narrow subset of the data.
Cross-validation
K-fold cross-validation
The original data is partitioned randomly into k folds. One fold is used for validation, while k-1 folds of data are used for hypothesis...
