Modeling Credit Scoring Framework Using Self-Organized Map and Hybrid Neural Network Ensembles
DOI:
https://doi.org/10.22399/ijcesen.3260Keywords:
Machine learning, Bankruptcy prediction, Classifier ensemble, Credit scoring,, Hybrid neural network classifierAbstract
assess the creditworthiness of both individuals and businesses. Evaluating the risk of business failure is especially significant for stakeholders like lenders and investors. Credit scoring provides a structured and data-driven method to predict these risks by analyzing financial, operational, and historical information. Applications of credit scoring include risk assessment, financial stability forecasting, trend identification, risk-based pricing, and default prediction. By providing a data-driven evaluation of credit risk, it enables institutions to make informed decisions, reduce potential losses, and improve risk management strategies. This research aims to bridge this gap by analyzing the effectiveness of neural network ensembles and hybrid neural network models using three standard credit scoring benchmark datasets: Australian, German, and Japanese. Experimental results show that while standalone neural networks achieve accuracies of 87.44%, 83.37%, and 85.08% respectively, ensemble models (weighted voting) improve performance to 92.75%, 89.34%, and 89.97%. Hybrid neural networks outperform both in the Australian dataset (93.61%), but show similar performance in the German (89.45%) and Japanese (89.17%) datasets. Although hybrid models demonstrate slightly higher accuracy on one dataset, the overall difference between hybrid and ensemble models is not statistically significant. This study provides a comprehensive comparative analysis to support the development of more accurate bankruptcy prediction systems and credit risk modeling strategies.
References
[1] F. Zhao and L. Ma, “Overfitting in neural credit scoring models and mitigation strategies,” J. Risk Finance, vol. 16, no. 1, pp. 34–48, 2025.
[2] D. Harrison and T. Nguyen, “Credit scoring with deep learning: Trends and challenges,” IEEE Trans. Ind. Inform., vol. 19, no. 2, pp. 1123–1132, 2025.
[3] L. Chen et al., “Statistical comparison of ensemble and hybrid neural networks for credit scoring,” IEEE Trans. Neural Netw. Learn. Syst., early access, May 2025.
[4] S. Patel and R. Gupta, “Economic impact of corporate bankruptcy: A review,” J. Finance Manage., vol. 58, no. 2, pp. 123–135, 2022.
[5] A. Gupta and V. Sharma, “Support vector machines in financial distress prediction,” J. Financial Data Sci., vol. 3, no. 2, pp. 34–47, 2022.
[6] Y. Li et al., “Ensemble deep learning for credit risk assessment,” IEEE Access, vol. 11, pp. 45890–458900, 2023.
[7] H. Huang et al., “Credit scoring models: A comprehensive review,” Expert Syst. Appl., vol. 212, p. 118, 2023.
[8] A. Kumar and B. Singh, “Deep architectures for bankruptcy prediction,” in Proc. Int. Conf. Data Sci., 2024, pp. 78–85.
[9] C. Zhang et al., “Support vector machines versus logistic regression in credit scoring,” J. Finance Technol., vol. 2, no. 1, pp. 15–28, 2022.
[10] J. Smith and P. Zhang, “Comparative study of machine learning algorithms for default prediction,” Fintech J., vol. 5, no. 4, pp. 210–222, 2024.
[11] P. Brown and S. Green, “Bagging approaches to credit risk prediction,” Expert Syst. Appl., vol. 190, p. 116, 2024.
[12] J. West et al., “Ensemble and hybrid models in financial prediction: A survey,” ACM Comput. Surv., vol. 55, no. 1, pp. 1–36, 2023.
[13] A. Tsai and K. Huang, “K-means clustering as a preprocessing step for credit scoring,” J. Comput. Finance, vol. 27, no. 3, pp. 67–84, 2023.
[14] M. Hsieh, “Hybrid clustering-classification frameworks for credit scoring,” Knowl.-Based Syst., vol. 270, pp. 109–121, 2022.
[15] T. Lin et al., “Comparative analysis of hybrid and ensemble neural models in bankruptcy forecasting,” Neurocomputing, vol. 441, pp. 92–104, 2021.
[16] N. Leshno and A. Spector, “Universal approximation capabilities of MLPs in bankruptcy forecasting,” IEEE Trans. Neural Netw., vol. 33, no. 8, pp. 4125–4134, 2022.
[17] M. Altman, “Financial ratios, discriminant analysis and the prediction of corporate bankruptcy,” J. Finance, vol. 23, no. 4, pp. 589–609, 1968.
[18] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[19] R. Chen et al., “Weighted voting ensembles for loan default classification,” Inf. Sci., vol. 650, pp. 304–317, 2024.
[20] S. Mitra et al., “Neuro-fuzzy systems for bankruptcy prediction,” IEEE Trans. Syst., Man, Cybern., vol. 33, no. 2, pp. 160–169, 2023.
[21] [21] Nalić, Jasmina, ZerinaMašetić, and Irfan Djedović. "Building Ensemble Models for Enhanced Credit Scoring: A Case Study from a Bosnian MicroFinancial Institution." 2024 47th MIPRO ICT and Electronics Convention (MIPRO). IEEE, 2024.
[22] [22] Qian, X., Cai, H.H., Innab, N. et al. A novel deep learning approach to enhance creditworthiness evaluation and ethical lending practices in the economy. Ann Oper Res 346, 1597–1619 (2025). https://doi.org/10.1007/s10479-024-05849-1
[23] [23] Addy, Wilhelmina Afua, et al. "AI in credit scoring: A comprehensive review of models and predictive analytics." Global Journal of Engineering and Technology Advances 18.02 (2024): 118-129.
[24] [24] Nallakaruppan, M. K., et al. "An Explainable AI framework for credit evaluation and analysis." Applied Soft Computing 153 (2024): 111307.
[25] [25] Lu, Wang, et al. "Corporate bond default prediction using bilateral topic information of credit rating reports." International Journal of Financial Engineering 11.03 (2024): 2443002.
[26] [26] Trinh, ToanKhang, and Daiyang Zhang. "Algorithmic fairness in financial decision-making: Detection and mitigation of bias in credit scoring applications." Journal of Advanced Computing Systems 4.2 (2024): 36-49.
[27] [27] Ziemba, P., Becker, J., Becker, A., & Radomska-Zalas, A. (2023). Framework for multi-criteria assessment of classification models for the purposes of credit scoring. Journal of Big Data, 10(1), 94.
[28] [28] Mohammadnejad-Daryani, H., Taleizadeh, A. A., & Pamucar, D. (2024). A novel profit-driven framework for model evaluation in credit scoring. Engineering Applications of Artificial Intelligence, 137, 109137.
[29] [29] Jovanovic, Z., Hou, Z., Biswas, K., & Muthukkumarasamy, V. (2024). Robust integration of blockchain and explainable federated learning for automated credit scoring. Computer Networks, 243, 110303.
[30] [30] Xu, Y., Kou, G., Peng, Y., Ding, K., Ergu, D., & Alotaibi, F. S. (2024). Profit-and risk-driven credit scoring under parameter uncertainty: A multiobjective approach. Omega, 125, 103004.
[31] [31] Hurlin, Christophe, Christophe Pérignon, and SébastienSaurin. "The fairness of credit scoring models." Management Science (2024).
[32] [32] Addy, Wilhelmina Afua, et al. "AI in credit scoring: A comprehensive review of models and predictive analytics." Global Journal of Engineering and Technology Advances 18.02 (2024): 118-129.
[33] [33] Rofik, Rofik, et al. "The optimization of credit scoring model using stacking ensemble learning and oversampling techniques." Journal of Information System Exploration and Research 2.1 (2024).
[34] Pertiwi, Dwika Ananda Agustina, et al. "Using genetic algorithm feature selection to optimize XGBoost performance in Australian credit." Journal of Soft Computing Exploration
[35] Olola, T. M., & Olatunde, T. I. (2025). Artificial Intelligence in Financial and Supply Chain Optimization: Predictive Analytics for Business Growth and Market Stability in The USA. International Journal of Applied Sciences and Radiation Research , 2(1). https://doi.org/10.22399/ijasrar.18
[36] Fowowe, O. O., & Agboluaje, R. (2025). Leveraging Predictive Analytics for Customer Churn: A Cross-Industry Approach in the US Market. International Journal of Applied Sciences and Radiation Research , 2(1). https://doi.org/10.22399/ijasrar.20
[37] Hafez, I. Y., & El-Mageed, A. A. A. (2025). Enhancing Digital Finance Security: AI-Based Approaches for Credit Card and Cryptocurrency Fraud Detection. International Journal of Applied Sciences and Radiation Research , 2(1). https://doi.org/10.22399/ijasrar.21
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering

This work is licensed under a Creative Commons Attribution 4.0 International License.