Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features

TL;DR

This study demonstrates that regularized target encoding significantly improves predictive performance in machine learning tasks involving high-cardinality categorical features, outperforming traditional encoding methods across various algorithms and datasets.

Contribution

The paper provides a comprehensive benchmark showing that regularized target encoding outperforms traditional encoding techniques in high-cardinality scenarios, offering practical guidelines for encoding choices.

Findings

Regularized target encoding yields the best predictive performance.

Traditional encodings like integer or leaf encoding are less effective.

The results are consistent across multiple algorithms and dataset types.

Abstract

Since most machine learning (ML) algorithms are designed for numerical inputs, efficiently encoding categorical variables is a crucial aspect in data analysis. A common problem are high cardinality features, i.e. unordered categorical predictor variables with a high number of levels. We study techniques that yield numeric representations of categorical variables which can then be used in subsequent ML applications. We focus on the impact of these techniques on a subsequent algorithm's predictive performance, and -- if possible -- derive best practices on when to use which technique. We conducted a large-scale benchmark experiment, where we compared different encoding strategies together with five ML algorithms (lasso, random forest, gradient boosting, k-nearest neighbors, support vector machine) using datasets from regression, binary- and multiclass- classification settings. In our study, regularized versions of target encoding (i.e. using target predictions based on the feature levels in the training set as a new numerical feature) consistently provided the best results. Traditionally widely used encodings that make unreasonable assumptions to map levels to integers (e.g. integer encoding) or to reduce the number of levels (possibly based on target information, e.g. leaf encoding) before creating binary indicator variables (one-hot or dummy encoding) were not as effective in comparison.