Comparative Analysis of the Performance of Machine Learning- Models in the Prediction of Credit Risk Assessment

Authors

  • Moses A. Kolnagbayan Department: Computer and Information Sciences, University of Liberia
  • Martin K. Wallace Department: Computer and Information Sciences, University of Liberia
  • Li Chow Department of Computer Science and Artificial Intelligence, Amity University, Jaipur
  • Darnette M. Herron Department: Computer and Information Sciences, University of Liberia
  • Francis Saah Department: Computer and Information Sciences, University of Liberia
  • Titus G. Gooding Department: Computer and Information Sciences, University of Liberia
  • Melvin I. Soclo Department of Information Technology, The United Methodist University, Monrovia, Liberia

Keywords:

credit risk assessment, financial institutions, machine learning, predictive

Abstract

This article conducts a comparative analysis of various machine learning models in predicting credit risk assessment. The study aims to discern the most effective model for enhancing accuracy and efficiency in this domain. Leveraging a comprehensive historical credit dataset with diverse borrower attributes and credit performance indicators, several machine learning algorithms, including K-Nearest Neighbors, decision trees, support vector machines, random forests, and Naive Bayes, were rigorously evaluated. Through meticulous data preprocessing and feature extraction techniques, the performance of each model was assessed using key evaluation metrics such as accuracy, precision, and recall. The findings highlight the superior predictive capabilities of certain models over others in identifying credit defaults and non-performing loans, shedding light on nuanced variable interactions influencing credit risk. This analysis serves as a valuable guide for financial institutions seeking to adopt the most effective machine learning model in their credit risk assessment processes.

References

. Crouhy, M., Galai, D., & Mark, R. (2000). A comparative analysis of current credit risk models. Journal of Banking & Finance, 24(1-2), 59-117.

. C. Agbonkhese, H.A. Soriyan & K. Mosaku (2023). The Efficiency of Machine Learning Algorithms in the Prediction of Drug Reactions in Clinical Settings. India Journal Of computer Science and Engineering, 14(6), 891 – 901

. O.C. Ngige, F.Y. Ayankoya, J. A. Balogun, E. Onuiri, C. Agbonkhese, and F.A. Sanusi (2023). A Dataset for predicting Supreme Court Judgement in Nigeria, Data in Brief 50(7): 109483.

. 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, 111-138.

. Chen, R., Wang, Z., Yang, L., Ng, C. T., & Cheng, T. C. E. (2022). A study on operational risk and credit portfolio risk estimation using data analytics. Decision sciences, 53(1), 84-123.

. Onay, C., & Öztürk, E. (2018). A review of credit scoring research in the age of Big Data. Journal of Financial Regulation and Compliance, 26(3), 382-405.

. 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, 111-138.

. Chen, H., Lee, T., & Wang, Q. (2020). Comparative Analysis of Machine Learning Techniques for Credit Risk Assessment. International Journal of Finance Studies, 8(3), 32-48.

. Wang, K., Zhang, L., & Huang, Y. (2015). Comparison of Support Vector Machines and Naive Bayes Models in Credit Risk Assessment. Journal of Financial Analytics, 4(1), 18-30.

. Kimani, J., Mugo, S., & Njau, P. (2019). Credit Risk Assessment Models in Microfinance Institutions. Microfinance Journal, 15(2), 120-135.

. 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, 111-138.

. Li, Y., & Zhou, H. (2021). Comparative Analysis of Credit Risk Models in Credit Card Transactions. International Journal of Banking Technology, 11(4), 180-195.

. Singh, A., & Gupta, R. (2018). Credit Risk Assessment in Peer-to-Peer Lending Platforms. Journal of Financial Technology, 4(3), 132-147.

. Zhang, Z., He, J., Zheng, H., Cao, J., Wang, G., & Shi, Y. (2023). Alternating minimization-based sparse least-squares classifier for accuracy and interpretability improvement of credit risk assessment. International Journal of Information Technology & Decision Making, 22(01), 537-567.

. Munkhdalai, L., Munkhdalai, T., Namsrai, O. E., Lee, J. Y., & Ryu, K. H. (2019). An empirical comparison of machine-learning methods on bank client credit assessments. Sustainability, 11(3), 699.

. Davis, R., Lo, A. W., Mishra, S., Nourian, A., Singh, M., Wu, N., & Zhang, R. (2022). Explainable machine learning models of consumer credit risk. Available at SSRN 4006840.

. Crook, J. N., Edelman, D. B., & Thomas, L. C. (2007). Recent developments in consumer credit risk assessment. European Journal of Operational Research, 183(3), 1447–1465. https://doi.org/10.1016/j.ejor.2006.09.100

. Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015). Benchmarking state-of-the-art machine learning techniques for credit scoring. Journal of the Operational Research Society, 66(6), 743–758. https://doi.org/10.1057/jors.2014.78

. Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., & Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the Operational Research Society, 54(6), 627–635. https://doi.org/10.1057/palgrave.jors.2601545

. Chen, M., Chen, X., & Wang, X. (2016). Diversity in multiple classifier systems: A review. Information Fusion, 36, 1–13. https://doi.org/10.1016/j.inffus.2016.09.001

Downloads

Published

2024-12-16

Issue

Section

Articles

How to Cite

Moses A. Kolnagbayan, Martin K. Wallace, Li Chow, Darnette M. Herron, Francis Saah, Titus G. Gooding, & Melvin I. Soclo. (2024). Comparative Analysis of the Performance of Machine Learning- Models in the Prediction of Credit Risk Assessment. International Journal of Computer (IJC), 52(1), 79-88. https://www.ijcjournal.org/InternationalJournalOfComputer/article/view/2281