Efficient Deep Learning Models for Accurate Default Loan Prediction in Credit Risk Management
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V7I1P106Keywords:
Credit Default Prediction, Deep Learning, Financial Risk Assessment, Loan Default Modeling, Machine Learning, Predictive AnalyticsAbstract
The increasing complexity of lending environments has enhanced the importance of complex credit risk measurement procedures that have the capacity of analyzing massive, nonlinear, and highly imbalanced financial information. To solve this, a deep-learning method was used to forecast credit defaults with the complete Lending Club data that contains a variety of demographic, behavioral, and financial attributes of borrowers. Data preparation was reliable due to rigorous preprocessing, includes using SMOTE to address missing data, outliers, and class imbalance. A comparison between ANN and ResNet, FKNN, and AdaBoost was created and compared. The results of studies show that ANN outperforms all other baseline models, achieving 98.92% accuracy, 98.08% precision, 99.2% recall, 99.1% specificity, 98.63% F1-score, and 0.99 AUC respectively. Additionally, the ROC curve and confusion matrix data confirm the good class-separation capacity and low rate of misclassification of the model. These results indicate the ANN usefulness in mimicking intricate borrower trends and improving predictive validity. On the whole, the findings demonstrate the importance of deep-learning methods to enhance credit risk evaluation and allow more effective, data-driven decision making in the framework of current automated underwriting systems.
References
[1] N. Malali, “Exploring Artificial Intelligence Models for Early Warning Systems with Systemic Risk Analysis in Finance,” in 2025 International Conference on Advanced Computing Technologies (ICoACT), IEEE, Mar. 2025, pp. 1–6. doi: 10.1109/ICoACT63339.2025.11005357.
[2] D. Patel, “Enhancing Banking Security: A Blockchain and Machine Learning- Based Fraud Prevention Model,” Int. J. Curr. Eng. Technol., vol. 13, no. 06, pp. 576–583, 2023, doi: 10.14741/ijcet/v.13.6.10.
[3] R. Q. Majumder, “A Review of Anomaly Identification in Finance Frauds Using Machine Learning Systems,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 5, no. 10, pp. 101–110, Apr. 2025, doi: 10.48175/IJARSCT-25619.
[4] O. Adekunle, S. Y. Alalade, T. Agbatogun, and C. Abimbola, “Credit risk management and financial performance of selected commercial banks in Nigeria,” J. Econ. & Financ. Stud., vol. 3, no. 01, pp. 1–9, 2015.
[5] S. J. Wawge, “A Survey on the Identification of Credit Card Fraud Using Machine Learning with Precision, Performance, and Challenges,” Int. J. Innov. Sci. Res. Technol., vol. 10, no. 4, pp. 3345–3352, May 2025, doi: 10.38124/ijisrt/25apr1813.
[6] B. R. Ande, “Federated Learning and Explainable AI for Decentralized Fraud Detection in Financial Systems,” J. Inf. Syst. Eng. Manag., vol. 10, no. 35s, pp. 48–56, 2025, doi: 10.52783/jisem.v10i35s.5921.
[7] R. Ma, “German Credit Risk Prediction Using Machine Learning Models,” in 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025), 2025, pp. 283–292. doi: 10.2991/978-94-6463-823-3_27.
[8] H. Kali, “Optimizing Credit Card Fraud Transactions identification and classification in banking industry Using Machine Learning Algorithms,” Int. J. Recent Technol. Sci. Manag., vol. 9, no. 11, pp. 85–96, 2024.
[9] S. B. Shah, “Advanced Framework for Loan Approval Predictions Using Artificial Intelligence-Powered Financial Inclusion Models,” in 2025 IEEE Integrated STEM Education Conference (ISEC), 2025, pp. 1–10. doi: 10.1109/ISEC64801.2025.11147327.
[10] R. Dattangire, R. Vaidya, D. Biradar, and A. Joon, “Exploring the Tangible Impact of Artificial Intelligence and Machine Learning: Bridging the Gap between Hype and Reality,” in 2024 1st International Conference on Advanced Computing and Emerging Technologies (ACET), IEEE, 2024, pp. 1–6. doi: 10.1109/ACET61898.2024.10730334.
[11] N. Prajapati, “The Role of Machine Learning in Big Data Analytics: Tools, Techniques, and Applications,” ESP J. Eng. Technol. Adv., vol. 5, no. 2, 2025, doi: 10.56472/25832646/JETA-V5I2P103.
[12] M. Ntow-Gyamfi and S. S. Boateng, “Credit risk and loan default among Ghanaian banks: An exploratory study,” Manag. Sci. Lett., vol. 3, no. 3, pp. 753–762, Mar. 2013, doi: 10.5267/j.msl.2013.01.015.
[13] V. Verma, “Deep Learning-Based Fraud Detection in Financial Transactions : A Case Study Using Real-Time Data Streams,” vol. 3, no. 4, pp. 149–157, 2023, doi: 10.56472/25832646/JETA-V3I8P117.
[14] I. Gasmi, S. Neji, N. Mansouri, and M. Soui, “Bank credit risk prediction using machine learning model,” Neural Comput. Appl., vol. 37, no. 16, pp. 10333–10350, Jun. 2025, doi: 10.1007/s00521-025-11044-5.
[15] W. Li, L. Yao, W. Li, and C. Ji, “Visualizing Credit Default Risk: Insights Through Machine Learning,” in 2025 7th International Conference on Software Engineering and Computer Science (CSECS), IEEE, Mar. 2025, pp. 1–6. doi: 10.1109/CSECS64665.2025.11009748.
[16] X. Long, “Development and Implementation of a Multilayer Deep Learning-Based Bank Credit Risk Forecasting System,” J. Inf. & Knowl. Manag., vol. 23, no. 04, p. 2450051, 2024.
[17] I. Aruleba and Y. Sun, “Effective Credit Risk Prediction Using Ensemble Classifiers With Model Explanation,” IEEE Access, vol. 12, pp. 115015–115025, 2024, doi: 10.1109/ACCESS.2024.3445308.
[18] M. Jumaa, M. Saqib, and A. Attar, “Improving Credit Risk Assessment through Deep Learning-based Consumer Loan Default Prediction Model,” Int. J. Financ. Bank. Stud., vol. 12, no. 1, pp. 85–92, Jun. 2023, doi: 10.20525/ijfbs.v12i1.2579.
[19] V. Kanaparthi, “Credit Risk Prediction using Ensemble Machine Learning Algorithms,” in 2023 International Conference on Inventive Computation Technologies (ICICT), IEEE, Apr. 2023, pp. 41–47. doi: 10.1109/ICICT57646.2023.10134486.
[20] A. Akinjole, O. Shobayo, J. Popoola, O. Okoyeigbo, and B. Ogunleye, “Ensemble-Based Machine Learning Algorithm for Loan Default Risk Prediction,” Mathematics, vol. 12, no. 21, p. 3423, Oct. 2024, doi: 10.3390/math12213423.
[21] P. Sharifi, V. Jain, M. Arab Poshtkohi, E. Seyyedi, and V. Aghapour, “Banks credit risk prediction with optimized ANN based on improved owl search algorithm,” Math. Probl. Eng., vol. 2021, no. 1, p. 8458501, 2021.
[22] D. K. Gupta and S. Goyal, “Credit Risk Prediction Using Artificial Neural Network Algorithm,” Int. J. Mod. Educ. Comput. Sci., vol. 10, no. 5, pp. 9–16, May 2018, doi: 10.5815/ijmecs.2018.05.02.
[23] V. Boguslauskas and R. Mileris, “Estimation of credit risk by artificial neural networks models,” Eng. Econ., vol. 64, no. 4, 2009.
[24] Y.-R. Chen, J.-S. Leu, S.-A. Huang, J.-T. Wang, and J.-I. Takada, “Predicting Default Risk on Peer-to-Peer Lending Imbalanced Datasets,” IEEE Access, vol. 9, pp. 73103–73109, 2021, doi: 10.1109/ACCESS.2021.3079701.
[25] V. Chang, S. Sivakulasingam, H. Wang, S. T. Wong, M. A. Ganatra, and J. Luo, “Credit Risk Prediction Using Machine Learning and Deep Learning: A Study on Credit Card Customers,” Risks, vol. 12, no. 11, p. 174, Nov. 2024, doi: 10.3390/risks12110174.
[26] A. Khashman, “Credit risk evaluation using neural networks: Emotional versus conventional models,” Appl. Soft Comput., vol. 11, no. 8, pp. 5477–5484, 2011.
[27] J.-Y. Kim and S.-B. Cho, “Towards Repayment Prediction in Peer-to-Peer Social Lending Using Deep Learning,” Mathematics, vol. 7, no. 11, 2019, doi: 10.3390/math7111041.
[28] Z. Hassani, M. Alambardar Meybodi, and V. Hajihashemi, “Credit Risk Assessment Using Learning Algorithms for Feature Selection,” Fuzzy Inf. Eng., vol. 12, no. 4, pp. 529–544, 2020, doi: 10.1080/16168658.2021.1925021.
[29] I. R. Berrada, F. Barramou, and O. B. Alami, “Towards a Machine Learning-based Model for Corporate Loan Default Prediction,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 3, pp. 565–573, 2024, doi: 10.14569/IJACSA.2024.0150357.
