A Hybrid Approach to Credit Risk Assessment Using Bill Payment Habits Data and Explainable Artificial Intelligence
Source abstract
Abstract
Credit risk is one of the most important issues in the rapidly growing and developing finance sector. This study utilized a dataset containing real information about the bill payments of individuals who made transactions with a payment institution operating in Turkey. First, the transactions in the dataset were analyzed based on the bill type and the individual and features reflecting the payment habits were extracted. For the target class, real credit scores generated by the Credit Registry Office for the individuals whose payment habits were extracted were used. The dataset is a multi-class, unbalanced, and alternative dataset. Therefore, the dataset was prepared for the analysis by using data cleaning, feature selection, and sampling techniques. Then, the dataset was classified using various classification and evaluation methods. The best results were obtained with a model consisting of ANOVA F-Test, SMOTE, and Extra Tree algorithms. With this model, 80.49% accuracy, 79.89% precision, and 97.04% UAC rate were obtained. These results are quite efficient for an alternative dataset with 10 classes. This model was transformed into an explainable and interpretable form using LIME and SHAP, which are XAI techniques. This study presents a new hybrid model for credit risk assessment based on a multi-class and imbalanced alternative dataset and machine learning.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Financial Distress and Bankruptcy Prediction
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Software Engineering, Istanbul Health and Technology University, Istanbul 34445, Turkey
Department of Computer Engineering, Istanbul University-Cerrahpasa, Istanbul 34320, Turkey
References (69)
Show source-provided references
1. Credit Scoring Models Using Ensemble Learning and Classification Approaches: A Comprehensive Survey10.1007/s11277-021-09158-9 ↗
2. Thomas, L., Crook, J., and Edelman, D. (2017). Chapter 1: The History and Philosophy of Credit Scoring. Credit Scoring and Its Applications, Society for Industrial and Applied Mathematics. [2nd ed.]. Mathematics in Industry.10.1137/1.9781611974560 ↗
3. Anatomy of the credit score10.1016/j.jebo.2011.05.005 ↗
4. Credit Scoring and Its Effects on the Availability and Affordability of Credit10.1111/j.1745-6606.2009.01151.x ↗
5. Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research10.1016/j.ejor.2015.05.030 ↗
6. A deep learning approach for credit scoring using credit default swaps10.1016/j.engappai.2016.12.002 ↗
7. Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects10.1016/j.ejor.2021.06.053 ↗
8. Wotawa, F., Friedrich, G., Pill, I., Koitz-Hristov, R., and Ali, M. (2019). Predicting the Listing Status of Chinese Listed Companies Using Twin Multi-class Classification Support Vector Machine. Advances and Trends in Artificial Intelligence. From Theory to Practice, Springer International Publishing. Lecture Notes in Computer Science.
9. Consumer credit risk: Individual probability estimates using machine learning10.1016/j.eswa.2013.03.019 ↗
10. Appel, A.P., Oliveira, V., Lima, B., Malfatti, G.L., de Santana, V.F., and de Paula, R. (2019). Optimize Cash Collection: Use Machine learning to Predicting Invoice Payment. arXiv.
11. Appropriate machine learning techniques for credit scoring and bankruptcy prediction in banking and finance: A comparative study10.3233/RDA-180051 ↗
12. A novel tree-based dynamic heterogeneous ensemble method for credit scoring10.1016/j.eswa.2020.113615 ↗
13. Application Analysis of Credit Scoring of Financial Institutions Based on Machine Learning Model10.1155/2021/9222617 ↗
14. Niu, B., Ren, J., and Li, X. (2019). Credit Scoring Using Machine Learning by Combing Social Network Information: Evidence from Peer-to-Peer Lending. Information, 10.10.3390/info10120397 ↗
15. What does your Facebook profile reveal about your creditworthiness? Using alternative data for microfinance10.1080/01605682.2018.1434402 ↗
16. Enhancing credit scoring with alternative data10.1016/j.eswa.2020.113766 ↗
17. Transparency, auditability, and explainability of machine learning models in credit scoring10.1080/01605682.2021.1922098 ↗
18. Nikolinakos, N.T. (2023). The Proposed Artificial Intelligence Act and Subsequent ‘Compromise’ Proposals: Commission, Council, Parliament. EU Policy and Legal Framework for Artificial Intelligence, Robotics and Related Technologies—The AI Act, Springer International Publishing.10.1007/978-3-031-27953-9_8 ↗
19. Toward interpretable credit scoring: Integrating explainable artificial intelligence with deep learning for credit card default prediction10.1007/s00521-023-09232-2 ↗
20. Feature contribution alignment with expert knowledge for artificial intelligence credit scoring10.1007/s11760-022-02239-7 ↗
21. Arai, K. (2023). A Systematic Review of Machine Learning and Explainable Artificial Intelligence (XAI) in Credit Risk Modelling. Proceedings of the Future Technologies Conference (FTC) 2022, Volume 1, Springer International Publishing.
22. Combining weighted SMOTE with ensemble learning for the class-imbalanced prediction of small business credit risk10.1007/s40747-021-00614-4 ↗
23. Empirical Analysis of Ensemble Learning for Imbalanced Credit Scoring Datasets: A Systematic Review10.1155/2022/6584352 ↗
24. Zhu, M., Zhang, Y., Gong, Y., Xu, C., and Xiang, Y. (2024). Enhancing Credit Card Fraud Detection A Neural Network and SMOTE Integrated Approach. arXiv.10.53469/jtpes.2024.04(02).04 ↗
25. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring10.1016/j.eswa.2017.02.017 ↗
26. Zhou, G., Zhang, Y., and Luo, S. (2018). P2P Network Lending, Loss Given Default and Credit Risks. Sustainability, 10.10.3390/su10041010 ↗
27. Chen, Q., Tsai, S.-B., Zhai, Y., Chu, C.-C., Zhou, J., Li, G., Zheng, Y., Wang, J., Chang, L.-C., and Hsu, C.-F. (2018). An Empirical Research on Bank Client Credit Assessments. Sustainability, 10.10.3390/su10051406 ↗
28. Awe, O.O., and Vance, E.A. (2025). Machine Learning Prediction of Multiclass Credit Score Classification. Practical Statistical Learning and Data Science Methods: Case Studies from LISA 2020 Global Network, USA, Springer International Publishing.
29. A benchmark of machine learning approaches for credit score prediction10.1016/j.eswa.2020.113986 ↗
30. Explainability of a Machine Learning Granting Scoring Model in Peer-to-Peer Lending10.1109/ACCESS.2020.2984412 ↗
31. Zhao, Z., and Bai, T. (2022). Financial Fraud Detection and Prediction in Listed Companies Using SMOTE and Machine Learning Algorithms. Entropy, 24.10.3390/e24081157 ↗
32. Gramegna, A., and Giudici, P. (2021). SHAP and LIME: An Evaluation of Discriminative Power in Credit Risk. Front. Artif. Intell., 4.10.3389/frai.2021.752558 ↗
33. An Explainable AI framework for credit evaluation and analysis10.1016/j.asoc.2024.111307 ↗
34. Naramala, V.K., Ravipudi, L.P., Bhavanam, S.P.R., Pokuri, V.N., Kumar, S.V.P., and Kishore, V.K. (2024, January 27–28). Prediction of Credit Card Fraud detection using Extra Tree Classifier and Data Balancing Methods. Proceedings of the 2024 IEEE 3rd World Conference on Applied Intelligence and Computing (AIC), Gwalior, India.10.1109/AIC61668.2024.10730885 ↗
35. Robust integration of blockchain and explainable federated learning for automated credit scoring10.1016/j.comnet.2024.110303 ↗
36. Explainable models of credit losses10.1016/j.ejor.2021.11.009 ↗
37. Alblooshi, M., Alhajeri, H., Almatrooshi, M., and Alaraj, M. (2024, January 1–2). Unlocking Transparency in Credit Scoring: Leveraging XGBoost with XAI for Informed Business Decision-Making. Proceedings of the 2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), Victoria, Seychelles.10.1109/ACDSA59508.2024.10467573 ↗
38. Pyle, D. (1999). Data Preparation for Data Mining, Morgan Kaufmann.
39. (2024, February 19). Statistical Analysis with Missing Data, Third Edition|Wiley Series in Probability and Statistics. Available online: https://onlinelibrary.wiley.com/doi/book/10.1002/9781119482260.
40. Class Noise vs. Attribute Noise: A Quantitative Study10.1007/s10462-004-0751-8 ↗
41. An introduction to variable and feature selection
42. Siham, A., Sara, S., and Abdellah, A. (2021, January 25–27). Feature selection based on machine learning for credit scoring: An evaluation of filter and embedded methods. Proceedings of the 2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), Kocaeli, Turkey.10.1109/INISTA52262.2021.9548410 ↗
43. Field, A. (2024). Discovering Statistics Using IBM SPSS Statistics, SAGE Publications.
44. Principal component analysis10.1039/C3AY41907J ↗
45. De Schutter, B., and van den Boom, T.J.J. (2001, January 25–27). Model predictive control for max-min-plus-scaling systems. Proceedings of the Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148), Arlington, VA, USA.10.1109/ACC.2001.945564 ↗
46. Herawan, T., Deris, M.M., and Abawajy, J. (2014). An Application of Oversampling, Undersampling, Bagging and Boosting in Handling Imbalanced Datasets. Proceedings of the First International Conference on Advanced Data and Information Engineering (DaEng-2013), Springer. Lecture Notes in Electrical Engineering.
47. Training and assessing classification rules with imbalanced data10.1007/s10618-012-0295-5 ↗
48. SMOTE: Synthetic Minority Over-sampling Technique10.1613/jair.953 ↗
49. He, H., Bai, Y., Garcia, E.A., and Li, S. (2008, January 1–8). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China.
50. A Noise-Filtered Under-Sampling Scheme for Imbalanced Classification10.1109/TCYB.2016.2606104 ↗
51. Asymptotic Properties of Nearest Neighbor Rules Using Edited Data10.1109/TSMC.1972.4309137 ↗
52. Two Modifications of CNN10.1109/TSMC.1976.4309452 ↗
53. A study of the behavior of several methods for balancing machine learning training data10.1145/1007730.1007735 ↗
54. Batista, G., Bazzan, A., and Monard, M.-C. (2003, January 3–5). Balancing Training Data for Automated Annotation of Keywords: A Case Study. Proceedings of the Workshop on Bioinformatics, Macaé, RJ, Brazil.
55. Decision trees: A recent overview10.1007/s10462-011-9272-4 ↗
56. Random Forests10.1023/A:1010933404324 ↗
57. Extremely randomized trees10.1007/s10994-006-6226-1 ↗
58. (2024, February 15). Pattern Recognition and Machine Learning. Available online: https://link.springer.com/book/9780387310732.
59. Rennie, J.D.M., Shih, L., Teevan, J., and Karger, D.R. (2003, January 21–24). Tackling the Poor Assumptions of Naive Bayes Text Classifiers. Proceedings of the 20th International Conference on Machine Learning (ICML-03), Washington, DC, USA.
60. Extreme Learning Machine for Multilayer Perceptron10.1109/TNNLS.2015.2424995 ↗
61. A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification10.1016/j.isprsjprs.2017.07.014 ↗
62. Estimation of prediction error by using K-fold cross-validation10.1007/s11222-009-9153-8 ↗
63. Evaluation performance recall and F2 score of credit card fraud detection unbalanced dataset using SMOTE oversampling technique10.1088/1742-6596/1918/4/042002 ↗
64. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
65. Carvalho, D.V., Pereira, E.M., and Cardoso, J.S. (2019). Machine Learning Interpretability: A Survey on Methods and Metrics. Electronics, 8.10.3390/electronics8080832 ↗
66. Ribeiro, M.T., Singh, S., and Guestrin, C. (2016). ‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier. arXiv.10.18653/v1/N16-3020 ↗
67. Arrow, K.J., Barankin, E.W., Blackwell, D., Bott, R., Dalkey, N., Dresher, M., Gale, D., Gillies, D.B., Glicksberg, I., and Gross, O. (1953). Contributions to the Theory of Games (AM-28), Volume II, Princeton University Press. Available online: https://www.jstor.org/stable/j.ctt1b9x1zv.
68. Lundberg, S.M., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, Curran Associates, Inc.. Available online: https://papers.nips.cc/paper_files/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-Abstract.html.
69. Interpretation of machine learning models using shapley values: Application to compound potency and multi-target activity predictions10.1007/s10822-020-00314-0 ↗