On Clustering Categories of Categorical Predictors in Generalized Linear Models

TL;DR

This paper introduces a clustering-based method to simplify categorical predictors in generalized linear models, reducing complexity and overfitting while maintaining or improving predictive accuracy.

Contribution

It presents a novel numerical approach to cluster categories, providing an interpretable proximity measure and demonstrating effectiveness on real datasets.

Findings

Clustering reduces model complexity significantly.

Method maintains or improves predictive accuracy.

Proximity measure enables visualization of category relationships.

Abstract

We propose a method to reduce the complexity of Generalized Linear Models in the presence of categorical predictors. The traditional one-hot encoding, where each category is represented by a dummy variable, can be wasteful, difficult to interpret, and prone to overfitting, especially when dealing with high-cardinality categorical predictors. This paper addresses these challenges by finding a reduced representation of the categorical predictors by clustering their categories. This is done through a numerical method which aims to preserve (or even, improve) accuracy, while reducing the number of coefficients to be estimated for the categorical predictors. Thanks to its design, we are able to derive a proximity measure between categories of a categorical predictor that can be easily visualized. We illustrate the performance of our approach in real-world classification and count-data datasets where we see that clustering the categorical predictors reduces complexity substantially without harming accuracy.