Measure

Custom 10-fold Crossvalidation

A custom holdout partitions a set of observations into a training set and a test set in a predefined way. This is typically done in order to compare the performance of different predictive algorithms on the same data, as part of a data mining competition or by the researcher who first uses the dataset.

Properties

Folds10
Repeats1
Holdout percentage
Stratified samplingfalse