Resampling strategies for imbalanced regression: a survey and empirical analysis

TL;DR

This paper provides a comprehensive survey and empirical analysis of resampling strategies for imbalanced regression problems, introducing a taxonomy and evaluating their effectiveness across various models and metrics.

Contribution

It introduces a taxonomy for imbalanced regression approaches and offers extensive experimental insights into the effectiveness of resampling strategies.

Findings

Resampling strategies improve model performance in imbalanced regression.

Different models benefit variably from resampling techniques.

The study highlights key directions for future research in imbalanced regression.

Abstract

Imbalanced problems can arise in different real-world situations, and to address this, certain strategies in the form of resampling or balancing algorithms are proposed. This issue has largely been studied in the context of classification, and yet, the same problem features in regression tasks, where target values are continuous. This work presents an extensive experimental study comprising various balancing and predictive models, and wich uses metrics to capture important elements for the user and to evaluate the predictive model in an imbalanced regression data context. It also proposes a taxonomy for imbalanced regression approaches based on three crucial criteria: regression model, learning process, and evaluation metrics. The study offers new insights into the use of such strategies, highlighting the advantages they bring to each model's learning process, and indicating directions for further studies. The code, data and further information related to the experiments performed herein can be found on GitHub: https://github.com/JusciAvelino/imbalancedRegression.