Research Article
Credit Card Default Prediction: A Comparative Analysis of Machine Learning Models and Ensemble Techniques
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357982, author={Ajaypradeep Natarajsivam and K. Hemasree and M. Divija and D. Celeena Priyanka and A. Gowthami}, title={Credit Card Default Prediction: A Comparative Analysis of Machine Learning Models and Ensemble Techniques}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={credit card default prediction machine learning ensemble learning random forest xgboost adaboost ann svm smote financial risk management}, doi={10.4108/eai.28-4-2025.2357982} }- Ajaypradeep Natarajsivam
K. Hemasree
M. Divija
D. Celeena Priyanka
A. Gowthami
Year: 2025
Credit Card Default Prediction: A Comparative Analysis of Machine Learning Models and Ensemble Techniques
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2357982
Abstract
CCDP is crucial for financial institutions to mitigate risks. While previous studies have primarily explored DT and AdaBoost models, limited research has assessed ensemble learning and DL techniques in this domain. Existing work often lacks transparency in feature selection, class imbalance handling, and computational efficiency analysis.This study evaluates multiple machine learning models, including LR, SVM, DT, RF, KNN, NB, ADB, ANN, and XGBoost. Unlike prior research, we employ outlier removal, feature scaling, and SMOTE to enhance model fairness. Our results show that Random Forest (85.97%) and XGBoost (85.06%) outperform AdaBoost (82%), contradicting previous findings. Additionally, execution time analysis highlights Random Forest and XGBoost as optimal trade-offs between accuracy and efficiency. This research provides a comprehensive evaluation of predictive models, offering valuable insights for improving credit risk assessment in banking.
