On dynamic ensemble selection and data preprocessing for multi-class imbalance learning

TL;DR

This paper empirically evaluates dynamic ensemble selection and data preprocessing techniques for multi-class imbalanced learning, demonstrating improvements over static ensembles and highlighting preprocessing's importance.

Contribution

It introduces an empirical analysis of dynamic selection and preprocessing methods specifically for multi-class imbalanced problems, an area with limited prior focus.

Findings

Dynamic ensembles outperform static ones in F-measure and G-mean.

Data preprocessing significantly impacts classification performance.

Multiple preprocessing variations contribute to improved results.

Abstract

Class-imbalance refers to classification problems in which many more instances are available for certain classes than for others. Such imbalanced datasets require special attention because traditional classifiers generally favor the majority class which has a large number of instances. Ensemble of classifiers have been reported to yield promising results. However, the majority of ensemble methods applied too imbalanced learning are static ones. Moreover, they only deal with binary imbalanced problems. Hence, this paper presents an empirical analysis of dynamic selection techniques and data preprocessing methods for dealing with multi-class imbalanced problems. We considered five variations of preprocessing methods and four dynamic selection methods. Our experiments conducted on 26 multi-class imbalanced problems show that the dynamic ensemble improves the F-measure and the G-mean as compared to the static ensemble. Moreover, data preprocessing plays an important role in such cases.