A Comparative Analysis of Machine Learning Models for Credit Default Prediction of Credit Card Customers of Taiwan Banks

DOI

10.2991/978-94-6463-823-3_20How to use a DOI?

Keywords

Machine Learning Models; Credit Default Prediction; Credit Card Customers of Taiwan Banks

Abstract

Credit card default prediction plays a crucial role in helping financial institutions reduce credit risk and maintain financial stability. As consumer credit usage continues to rise, accurate default prediction enables better decision-making and protects the financial system. This study provides empirical evidence for financial institutions to optimize risk management strategies. This study examines the applicability of various machine learning models in actual financial settings by comparing them for forecasting credit defaults among credit card clients of Taiwanese banks. This paper used the Logistic Regression, Random Forest, Gradient Boosting, and Linear Regression models to analyze the credit card market and default factors in Taiwan. Accuracy, F1 Score, and Area Under the Curve metrics (AUC) were used to assess the models following data preprocessing, which included normalization and train-test separation. Gradient Boosting outperformed Random Forest with 81.98% accuracy and 0.783 AUC, according to the results. Recent payment history was found to be the most reliable indicator of default by feature significance analysis. Financial institutions can optimize their risk management methods with the empirical evidence provided by this study.

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  - Tianran Shi
PY  - 2025
DA  - 2025/08/31
TI  - A Comparative Analysis of Machine Learning Models for Credit Default Prediction of Credit Card Customers of Taiwan Banks
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 218
EP  - 226
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_20
DO  - 10.2991/978-94-6463-823-3_20
ID  - Shi2025
ER  -