Credit Card Default Prediction with Data Modeling

DOI

10.2991/978-94-6463-198-2_155How to use a DOI?

Keywords

Credit card default; Predictive modeling; Credit risk assessment

Abstract

This paper aims to build a predictive model to identify credit card default and minimize losses for financial institutions. The study uses data from the Credit Card Approval Prediction dataset on Kaggle, with 36,457 rows and 17 predictors. The credit card default is an unbalanced outcome variable, with most customers paying their credit card balance on time. The authors compare four models (logistic regression, KNN, random forest, and XGBoost) in terms of AUC, F1 score, accuracy, precision, and recall. The random forest and XGBoost models perform the best with AUC scores of 0.771 and 0.753, respectively. The findings suggest that the use of predictive models can help financial institutions identify good and bad customers and make better decisions regarding issuing credit cards.

Copyright

© 2023 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  - Zhaohong Wang
AU  - Cheng Han Wen
AU  - Wenda Zhou
AU  - Jun Zhang
PY  - 2023
DA  - 2023/08/10
TI  - Credit Card Default Prediction with Data Modeling
BT  - Proceedings of the 2nd International Academic Conference on Blockchain, Information Technology and Smart Finance (ICBIS 2023)
PB  - Atlantis Press
SP  - 1494
EP  - 1503
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-198-2_155
DO  - 10.2991/978-94-6463-198-2_155
ID  - Wang2023
ER  -