Nghiên cứu mô hình học máy dự đoán xác suất vỡ nợ của khách hàng doanh nghiệp tại ngân hàng thương mại cổ phần ở Việt Nam
DOI:
https://doi.org/10.24311/jabes/2023.34.8.6Abstract
Predicting the probability of customer default in the future using modern technologies is a growing trend in the overall financial industry, specifically in the banking sector. It is necessary for financial institutions to have timely solutions such as credit risk reduction, credit process analysis, and credit portfolio optimization. The paper utilizes data related to credit information, financial indicators, and corporate customer characteristics from the bank, employing quantitative research methods to collect and process data to build a machine-learning model. The result shows that the XGBoost model achieved the highest accuracy with an F1-score of 0.84, and the ROC curve had an AUC of 0.97. By utilizing these findings, the bank can implement the model into practice to facilitate business decision-making, enhance credit risk forecasting capabilities, improve operational efficiency, and mitigate undesirable losses.
References
Boughaci, D., Alkhawaldeh, A. A. K., Jaber, J. J., & Hamadneh, N. (2021). Classification with segmentation for credit scoring and bankruptcy prediction. Empirical Economics, 61(3), 1281–1309. doi:10.1007/s00181-020-01901-8
Brownlee, J. (2020). Imbalanced Classification with Python: Better Metrics, Balance Skewed Classes, Cost-Sensitive Learning: Machine Learning Mastery.
Phạm Quốc Chiến, & Nguyễn Thị Thúy Quỳnh. (2022). Nâng cao chất lượng tín dụng bằng chấm điểm khách hàng tại Ngân hàng Nông nghiệp và Phát triển Nông thôn chi nhánh huyện Mường Ảng, Điện Biên. Tạp chí Khoa học (Trường Đại học Tây Bắc), 25, 31–36.
Addo, P.M., Guegan, D., & Hassani, B. (2018). Credit Risk Analysis Using Machine and Deep Learning Models. Computational Methods for Risk Management in Economics and Finance, 6(2), 38. doi:10.3390/risks6020038
Guegan, D., Addo, P., & Hassani, B. (2018). Credit Risk Analysis Using Machine and Deep Learning Models. Computational Methods for Risk Management in Economics and Finance, 6(2), 38. doi:10.3390/risks6020038
Hoàng Thanh Hải, Trần Đình Chúc, & Nguyễn Quỳnh Hoa. (2018). Mô hình hồi quy Logistic trong đo lường xác suất vỡ nợ khách hàng tín dụng cá nhân. Tạp chí Kinh tế & Quản trị Kinh doanh, 7, 92–100.
Đặng Thị Thu Hằng. (2019). Ứng dụng mô hình logistic trong quản trị rủi ro tín dụng. Tạp chí Thị trường Tài chính Tiền tệ, 11, 30–34.
Phi Hồng Hạnh. (2015). Đánh giá khả năng trả nợ của doanh nghệp bằng ứng dụng Mô hình Logit. Tạp chí Khoa học & Đào tạo Ngân hàng, 155, 45–51.
Gonzales, F., Haas, F., Persson, M., Toledo, L., Violi, R., Wieland, M., & Zins, C. (2004). Market dynamics associated with credit ratings: A literature review. European Central Bank Occasional Paper Series, 16.
Krawczyk, B. (2016). Learning from imbalanced data: open challenges and future directions. Progress in Artificial Intelligence, 5(4), 221–232. doi:10.1007/s13748-016-0094-0
Li, B., Xiao, B., & Yang, Y. (2021). Strengthen credit scoring system of small and micro businesses with soft information: Analysis and comparison based on neural network models. Journal of Intelligent & Fuzzy Systems, 40, 1–18. doi:10.3233/JIFS-200866
Luo, Z., Hsu, P., & Xu, N. (2020). SME default prediction framework with the effective use of external public credit data. Sustainability, 12, 7575. doi:10.3390/su12187575
Maddala, G. S. (1983). Limited-Dependent and Qualitative Variables in Econometrics. Cambridge: Cambridge University Press.
Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. Cambridge, Massachusetts, London, England: MIT press.
Nikolic, N., Zarkic-Joksimovic, N., Stojanovski, D., & Joksimovic, I. (2013). The application of brute force logistic regression to corporate credit scoring models: Evidence from Serbian financial statements. Expert Systems with Applications, 40(15), 5932–5944. doi:10.1016/j.eswa.2013.05.022
Rose, & Hudgins. (2015). Bank Management and Financial Services. New York: McGraw-Hill.
Siddiqi, N. (2016). Intelligent Credit Scoring: Building and Implementing Better Credit Risk Scorecards, Second Edition. Wiley.
Đỗ Năng Thắng, & Nguyễn Văn Huân (2019). Đề xuất cảnh báo rủi ro trong cho vay khách hàng doanh nghiệp của ngân hàng thương mại ở Việt Nam. Tạp Chí Khoa học thương mại, 131, 55–63.
Wang, Z., Jiang, C., Ding, Y., Lyu, X., & Liu, Y. (2018). A Novel behavioral scoring model for estimating probability of default over time in peer-to-peer lending. Electronic Commerce Research and Applications, 27, 74–82. doi:10.1016/j.elerap.2017.12.006
Yuan, K., Chi, G., Zhou, Y., & Yin, H. (2021). A novel two-stage hybrid default prediction model with k-means clustering and support vector domain description. Research in International Business and Finance, 59, 101536. doi:10.1016/j.ribaf.2021.101536
Zekic-Susac, M., Sarlija, N., & Benšić, M. (2004). Small business credit scoring: A comparison of logistic regression, neural network, and decision tree models. In 26th International Conference on Information Technology Interfaces, 265–270.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JOURNAL OF ASIAN BUSINESS AND ECONOMIC STUDIES
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
