Dynamic Ensemble Learning for Credit Scoring: A Comparative Study

TL;DR

This paper benchmarks various dynamic ensemble selection techniques for credit scoring, demonstrating their effectiveness in improving model performance, especially in imbalanced data scenarios, on real-world high-dimensional datasets.

Contribution

It provides a systematic comparison of dynamic selection methods for ensemble learning in credit scoring, highlighting their advantages in real-life, high-dimensional, and imbalanced data contexts.

Findings

Dynamic selection techniques improve ensemble performance in credit scoring.

These techniques are particularly effective in imbalanced data environments.

Ensemble models with dynamic selection outperform static models on real-world datasets.

Abstract

Automatic credit scoring, which assesses the probability of default by loan applicants, plays a vital role in peer-to-peer lending platforms to reduce the risk of lenders. Although it has been demonstrated that dynamic selection techniques are effective for classification tasks, the performance of these techniques for credit scoring has not yet been determined. This study attempts to benchmark different dynamic selection approaches systematically for ensemble learning models to accurately estimate the credit scoring task on a large and high-dimensional real-life credit scoring data set. The results of this study indicate that dynamic selection techniques are able to boost the performance of ensemble models, especially in imbalanced training environments.