Evaluating the Efficacy of Machine Learning Algorithms in Credit Card Limit Optimization and Customer Segmentation
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V3I3P106Keywords:
Credit card limit optimization, Customer segmentation, Machine learning, Clustering, Regression, Financial analytics, Random Forest, K-Means, SHAP, Fairness in AIAbstract
The Digital age of finance, the use of Machine Learning (ML) in credit cards introduces a new breed of mainstream approach to ensure that not only are operations made efficient, but also customer satisfaction is optimized. Two of such areas where ML algorithms can be of great value are credit card limit optimization and segmentation of customers. The paper will look at the efficiency of some supervised and unsupervised ML models, such as Logistic Regression, Decision Trees, Random Forests, K-Means Clustering, and DBSCAN, to optimize credit card limits and cluster customers based on the behavioral information. The data is part of a large-scale record of a large financial institution, and includes anonymized profiles (profiles of customers), history of transactions, credit limit, history of payments (repaying) and demographic information. A proper dataset with appropriate modeling was achieved via the intensive preparation process (preprocessing and feature engineering). The regression formulation was treated by the problem of limit optimization, and segmentation has been dealt with through clustering. Model fit was checked with such measures as Mean Squared Error (MSE), R-squared, Silhouette Score, and Davies-Bouldin Index. We have found that ensemble learning algorithms such as Random Forest have a better prediction accuracy when it comes to estimating optimum credit limits, and that K-Means clustering, on the other hand, delivers satisfactory customer segregation that can be used relative to targeting financial products. Interpretability and fairness issues are also addressed in this paper with the help of SHAP values and analysis of demographic parity. By implementing ML in their credit systems, financial institutions can considerably limit the risk factor, individually tailor activities, and promote customer retention. Finally, we will discuss in the conclusion deployment strategies, ethical implications and possible future studies
Downloads
References
[1] Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
[2] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016, August). "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).
[3] Hand, D. J., & Henley, W. E. (1997). Statistical classification methods in consumer credit scoring: a review. Journal of the royal statistical society: series a (statistics in society), 160(3), 523-541.
[4] Lessmann, S., Baesens, B., Seow, H. V., & Thomas, L. C. (2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124-136.
[5] Moro, S., Cortez, P., & Rita, P. (2014). A data-driven approach to predicting the success of bank telemarketing. Decision Support Systems, 62, 22-31.
[6] Kamiran, F., Calders, T., & Pechenizkiy, M. (2013). Techniques for discrimination-free predictive models. Discrimination and privacy in the information society: data mining and profiling in large databases, 223-239.
[7] Brown, I., & Mues, C. (2012). An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert systems with applications, 39(3), 3446-3453.
[8] Baesens, B., Bapna, R., Marsden, J. R., Vanthienen, J., & Zhao, J. L. (2016). Transformational issues of big data and analytics in networked business. MIS quarterly, 40(4), 807-818.
[9] Jain, A. K., Murty, M. N., & Flynn, P. J. (1999). Data clustering: a review. ACM computing surveys (CSUR), 31(3), 264-323.
[10] Hardt, M., Price, E., & Srebro, N. (2016). Equality of opportunity in supervised learning. Advances in neural information processing systems, 29.
[11] Binns, R. (2018, January). Fairness in machine learning: Lessons from political philosophy. In Conference on fairness, accountability and transparency (pp. 149-159). PMLR.
[12] Bhatore, S., Mohan, L., & Reddy, Y. R. (2020). Machine learning techniques for credit risk evaluation: a systematic literature review. Journal of Banking and Financial Technology, 4(1), 111-138.
[13] Dastile, X., & Celik, T. (2021). Making deep learning-based predictions for credit scoring explainable. IEEE Access, 9, 50426-50440.
[14] Singh, P. (2009). Comparing the effectiveness of machine learning algorithms for defect prediction. International Journal of Information Technology and Knowledge Management, 2(2), 481-483.
[15] Li, W., Wu, X., Sun, Y., & Zhang, Q. (2010, December). Credit card customer segmentation and target marketing based on data mining. In 2010 International Conference on Computational Intelligence and Security (pp. 73-76). IEEE.
[16] Ho, H., Tien, K. M. T., Wu, A., & Singh, S. (2021). A sequence analysis approach to segmenting credit card customers. Journal of Retailing and Consumer Services, 59, 102391.
[17] Budd, J. K., & Taylor, P. G. (2015). Calculating optimal limits for transacting credit card customers. arXiv preprint arXiv:1506.05376.
[18] Bouwmeester, W., Twisk, J. W., Kappen, T. H., van Klei, W. A., Moons, K. G., & Vergouwe, Y. (2013). Prediction models for clustered data: comparison of a random intercept and standard regression model. BMC Medical Research Methodology, 13, 1-10.
[19] Raj, A., Bosch, J., Olsson, H. H., & Wang, T. J. (2020, August). Modelling data pipelines. In 2020, the 46th Euromicro conference on software engineering and advanced applications (SEAA) (pp. 13-20). IEEE.
[20] Woldeyohannes, A. D., & Abd Majid, M. A. (2011). Simulation model for natural gas transmission pipeline network system. Simulation Modelling Practice and Theory, 19(1), 196-212.
[21] Yuping, Z., Jílková, P., Guanyu, C., & Weisl, D. (2020, March). New methods of customer segmentation and individual credit evaluation based on machine learning. In “New Silk Road: Business Cooperation and Prospective of Economic Development”(NSRBCPED 2019) (pp. 925-931). Atlantis Press.
