Enhanced Loan Approval Prediction Using a Cascaded Machine Learning Framework

Yıl 2026, Cilt: 21 Sayı: 1 , 258 - 278 , 01.04.2026

Ahmet Akusta

https://doi.org/10.17153/oguiibf.1596734

https://izlik.org/JA46XN96JB

Öz

This study introduces a multi-stage cascaded machine learning framework for loan approval prediction, which addresses the inefficiencies inherent in traditional processes. The framework combines Gradient Boosting, Support Vector Machine, and XGBoost to refine predictions at each stage. This approach allows the framework to leverage the strengths of each technique in order to handle complex relationships and imbalanced data. The framework was tested on a comprehensive financial dataset, demonstrating the critical role of Gradient Boosting and traditional features like home ownership in improving predictive accuracy. The research illustrates the framework's capacity to augment credit risk assessment, curtail defaults, and facilitate decision-making, providing financial institutions with a robust instrument for operational efficiency and financial stability.

Anahtar Kelimeler

Loan Approval Prediction , Cascaded Machine Learning , Credit Risk Assessment , Financial Decision-Making , Risk Management

Çok Katmanlı Makine Öğrenimi Çerçevesi ile Gelişmiş Kredi Onay Tahmini

https://izlik.org/JA46XN96JB

Öz

Bu çalışma, kredi onayı tahmini için geleneksel süreçlerin doğasında bulunan verimsizlikleri ele alan çok aşamalı kademeli bir makine öğrenimi çerçevesi sunmaktadır. Çerçeve, her aşamada tahminleri iyileştirmek için Gradient Boosting, Destek Vektör Makinesi ve XGBoost'u birleştirmektedir. Bu yaklaşım, çerçevenin karmaşık ilişkileri ve dengesiz verileri ele almak için her tekniğin güçlü yönlerinden yararlanmasını sağlar. Çerçeve, Gradient Boosting'in ve ev sahipliği gibi geleneksel özelliklerin tahmin doğruluğunu artırmadaki kritik rolünü gösteren kapsamlı bir finansal veri kümesi üzerinde test edilmiştir. Araştırma, çerçevenin kredi riski değerlendirmesini artırma, temerrütleri azaltma ve karar vermeyi kolaylaştırma kapasitesini göstermekte ve böylece finansal kurumlara operasyonel verimlilik ve finansal istikrar için sağlam bir araç sağlamaktadır.

Anahtar Kelimeler

Kredi Onay Tahmini , Basamaklı Makine Öğrenimi , Kredi Risk Değerlendirmesi , Finansal Karar Alma , Risk Yönetimi

Kaynakça

• Abakarim, Y., Lahby, M., & Attioui, A. (2018). Towards an efficient real-time approach to loan credit approval using deep learning. 9th International Symposium on Signal, Image, Video and Communications, ISIVC 2018 - Proceedings, 306–313. https://doi.org/10.1109/ISIVC.2018.8709173
• Alagic, A., Zivic, N., Kadusic, E., Hamzic, D., Hadzajlic, N., Dizdarevic, M., & Selmanovic, E. (2024). Machine learning for an enhanced credit risk analysis: A comparative study of loan approval prediction models integrating mental health data. Machine Learning and Knowledge Extraction, 6(1), 53–77. https://doi.org/10.3390/make6010004
• Aleksandrova, Y., & Armianova, M. (2022). Evaluation of cost-sensitive machine learning methods for default credit prediction. International Conference Automatics and Informatics, ICAI 2022 - Proceedings, 89–94. https://doi.org/10.1109/ICAI55857.2022.9960023
• Alessi, L., & Savona, R. (2021). Machine learning for financial stability. In Data science for economics and finance: Methodologies and applications (pp. 65–87). https://doi.org/10.1007/978-3-030-66891-4_4
• Antonelli, M., Bernardo, D., Hagras, H., & Marcelloni, F. (2017). Multiobjective evolutionary optimization of type-2 fuzzy rule-based systems for financial data classification. IEEE Transactions on Fuzzy Systems, 25(2), 249–264. https://doi.org/10.1109/TFUZZ.2016.2578341
• Borchani, H., Martínez, A. M., Masegosa, A. R., Langseth, H., Nielsen, T. D., Salmerón, A., Fernández, A., Madsen, A. L., & Sáez, R. (2015). Dynamic Bayesian modeling for risk prediction in credit operations. Frontiers in Artificial Intelligence and Applications, 278, 17–26. https://doi.org/10.3233/978-1-61499-589-0-17
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
• Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August 2016, 785–794. https://doi.org/10.1145/2939672.2939785
• Cheng, C., Xu, W., & Wang, J. (2012). A comparison of ensemble methods in financial market prediction. Proceedings of the 2012 5th International Joint Conference on Computational Sciences and Optimization, CSO 2012, 755–759. https://doi.org/10.1109/CSO.2012.171
• Deepa, M., Pal, S., & Ghusey, V. P. (2024). Monetary loan eligibility prediction using logistic regression algorithm. 2nd International Conference on Emerging Trends in Information Technology and Engineering, Ic-ETITE 2024. https://doi.org/10.1109/ic-ETITE58242.2024.10493584
• Ding, Z. (2023). Construction and exploration of a financial risk control model based on machine learning. 2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023. https://doi.org/10.1109/EASCT59475.2023.10393547
• García, V., Marqués, A. I., & Sánchez, J. S. (2019). Exploring the synergetic effects of sample types on the performance of ensembles for credit risk and corporate bankruptcy prediction. Information Fusion, 47, 88–101. https://doi.org/10.1016/j.inffus.2018.07.004
• Garg, D., Shelke, N. A., Kitukale, G., & Mehlawat, N. (2024). Leveraging financial data and risk management in banking sector using machine learning. 2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024. https://doi.org/10.1109/I2CT61223.2024.10544336
• Gupta, A., Pant, V., Kumar, S., & Bansal, P. K. (2020). Bank loan prediction system using machine learning. Proceedings of the 2020 9th International Conference on System Modeling and Advancement in Research Trends, SMART 2020, 423–426. https://doi.org/10.1109/SMART50582.2020.9336801
• Gupta, H. (2024). Credit Risk Dataset, Version 1. Retrieved October 5, 2024, from https://www.kaggle.com/datasets/harshg97/credit-risk-dataset/versions/1
• Hussain, M. Z., Ejaz, S., Batool, E., Hasan, M. Z., Mustafa, M., Khalid, A., Hussain, U., Khan, Z., Javaid, A., Ashraf, M. F., Awan, R., & Yaqub, M. A. (2024). Bank loan prediction system using machine learning models. 2024 IEEE 9th International Conference for Convergence in Technology, I2CT 2024. https://doi.org/10.1109/I2CT61223.2024.10543786
• Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 2017-December, 3147–3155. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85038215940&partnerID=40&md5=e7f6611aa423276ab95bd73aa45ad93e
• Lenka, S. R., Pant, M., Barik, R. K., Patra, S. S., & Dubey, H. (2021). Investigation into the efficacy of various machine learning techniques for mitigation in credit card fraud detection. Advances in Intelligent Systems and Computing, 1176, 255–264. https://doi.org/10.1007/978-981-15-5788-0_24
• Li, T., & Dai, X. (2024). Financial risk prediction and management using machine learning and natural language processing. International Journal of Advanced Computer Science and Applications, 15(6), 211–219. https://doi.org/10.14569/IJACSA.2024.0150623
• Liu, Z., & Li, D. (2024). Research of Dempster-Shafer’s theory and ensemble classifier financial risk early warning model based on Benford’s law. Computational Economics. https://doi.org/10.1007/s10614-024-10679-1
• Luo, S., Xing, M., & Zhao, J. (2022). Construction of artificial intelligence application model for supply chain financial risk assessment. Scientific Programming, 2022. https://doi.org/10.1155/2022/4194576
• Meshref, H. (2020). Predicting loan approval of bank direct marketing data using ensemble machine learning algorithms. International Journal of Circuits, Systems and Signal Processing, 14, 914–922. https://doi.org/10.46300/9106.2020.14.117
• Mistry, K. A. J., & Mandal, B. (2024). Unified deep ensemble architecture for multiple classification tasks. Lecture Notes in Networks and Systems, 1065 LNNS, 544–557. https://doi.org/10.1007/978-3-031-66329-1_35
• Nagaraj, P., Nikhil, K., Sai Ram Santosh Babu, K. V. S., Reddy, D. H. T., Sekar, R. R., & Rajkumar, T. D. (2023). Loan prediction analysis using innumerable machine learning algorithms. 2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023. https://doi.org/10.1109/ICDSAAI59313.2023.10452622
• Nishanth, K. J., & Ravi, V. (2016). Probabilistic neural network based categorical data imputation. Neurocomputing, 218, 17-25. https://doi.org/10.1016/j.neucom.2016.08.044
• Nugroho, H., Utama, N. P., & Surendro, K. (2023). Smoothing target encoding and class center-based firefly algorithm for handling missing values in categorical variable. Journal of Big Data, 10(1), 10. https://doi.org/10.1186/s40537-022-00679-z
• Oliveira, L. S., Britto Jr., A. S., & Sabourin, R. (2005). Improving cascading classifiers with particle swarm optimization. Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, 2005, 570–574. https://doi.org/10.1109/ICDAR.2005.138
• Oualid, A., Maleh, Y., & Moumoun, L. (2023). Federated learning techniques applied to credit risk management: A systematic literature review. EDPACS, 68(1), 42–56. https://doi.org/10.1080/07366981.2023.2241647
• Pandey, T. N., Jagadev, A. K., Choudhury, D., & Dehuri, S. (2013). Machine learning-based classifiers ensemble for credit risk assessment. International Journal of Electronic Finance, 7(3–4), 227–249. https://doi.org/10.1504/IJEF.2013.058604
• Pavithrakannan, R., Fenn, N. B., Raman, S., Kalyanaraman, V., Murugananthan, V. K., & Janarthanan, J. (2021). Imputation analysis of central tendencies for classification. 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), 1-7. https://doi.org/10.1109/IEMTRONICS52119.2021.9422507
• Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
• Pimcharee, K., & Surinta, O. (2022). Data mining approaches in personal loan approval. Engineering Access, 8(1), 15–21. https://doi.org/10.14456/mijet.2022.2
• Rehberger, M., & Hiete, M. (2020). Allocation of environmental impacts in circular and cascade use of resources: Incentive-driven allocation as a prerequisite for cascade persistence. Sustainability (Switzerland), 12(11). https://doi.org/10.3390/su12114366
• Santos, G. D., & Lima, K. R. (2024). Impact of combinatorial optimization on reinforcement learning for stock trading in financial markets. ACM International Conference Proceeding Series. https://doi.org/10.1145/3658271.3658282
• Sarisa, H. K., Khurana, V., Koti, V. C., & Garg, N. (2023). Loan prediction using machine learning. 2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023, 194–198. https://doi.org/10.1109/ICAICCIT60255.2023.10466049
• Sarkar, T., Rakhra, M., Sharma, V., & Singh, A. (2024). An empirical comparison of machine learning techniques for bank loan approval prediction. Proceedings of International Conference on Communication, Computer Sciences and Engineering, IC3SE 2024, 137–143. https://doi.org/10.1109/IC3SE62002.2024.10593355
• Shingi, G. (2020). A federated learning-based approach for loan defaults prediction. IEEE International Conference on Data Mining Workshops, ICDMW, 2020-November, 362–368. https://doi.org/10.1109/ICDMW51313.2020.00057
• Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2), 241–259. https://doi.org/10.1016/S0893-6080(05)80023-1
• Yemmanuru, P. K., Yeboah, J., & Nti, I. K. (2024). Customer credit risk: Application and evaluation of machine learning and deep learning models. 2024 IEEE 3rd International Conference on Computing and Machine Intelligence, ICMI 2024 - Proceedings. https://doi.org/10.1109/ICMI60790.2024.10585896
• Zhang, L., Wang, J., & Liu, Z. (2023). What should lenders be more concerned about? Developing a profit-driven loan default prediction model. Expert Systems with Applications, 213. https://doi.org/10.1016/j.eswa.2022.118938
• Zhou, Y., Xiao, Z., Gao, R., & Wang, C. (2024). Using data-driven methods to detect financial statement fraud in the real scenario. International Journal of Accounting Information Systems, 54. https://doi.org/10.1016/j.accinf.2024.100693