Feature selection for machine learning models

Abstract

Methods and systems are described herein for facilitating segmentation of training data using measures of statistical dispersion (e.g., Gini impurities) of dataset features. The system determines, from a training dataset, a target feature and candidate features. The system determines, for the target feature in relation to each candidate feature, first Gini impurities. The system selects a first and second feature having the lowest first Gini impurities. The system determines, for the target feature in relation to a first combination of the first and second features, a second Gini impurity. If the second Gini impurity does not satisfy a threshold, the system selects a third feature having the next lowest first Gini impurity and determines a third Gini impurity for a second combination of the first, second, and third features. If the third Gini impurity satisfies the threshold, the system trains a model using the target, first, second, and third features.