Comparative Analysis of Machine Learning Models for Predicting Credit Card Default

DOI

10.2991/978-94-6463-823-3_26How to use a DOI?

Keywords

Credit Card; Risk Prediction; Machine Learning

Abstract

Credit card default risk prediction is a key field of risk management in financial institutions, and its accuracy directly affects the quality of credit assets and the stability of financial markets. Traditional prediction methods (such as statistical analysis, rule engines and expert systems) are limited by the lack of model flexibility, difficulty in extracting high-dimensional features and high cost of manual intervention. In contrast, machine learning (ML) methods can effectively improve prediction performance by automatically capturing nonlinear feature. This study systematically assesses and compares the efficacy of seven prominent ML models—Logistic Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Naive Bayes (NB), Extreme Gradient Boosting (XGBoost), Random Forest (RF) and Gradient Boosting (GB)—for predicting credit card payment defaults. The experimental comparison focuses on three critical evaluation metrics—accuracy, predictive precision, and the area under the Receiver Operating Characteristic curve (AUC-ROC). The gradient boosting model (AUC = 0.812) approach outperforms alternative methods in Default of Credit Card Clients dataset, outperforming other methods, and its ensemble learning mechanism shows strong robustness to class imbalanced data..

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lin Hou
PY  - 2025
DA  - 2025/08/31
TI  - Comparative Analysis of Machine Learning Models for Predicting Credit Card Default
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 274
EP  - 282
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_26
DO  - 10.2991/978-94-6463-823-3_26
ID  - Hou2025
ER  -