CFP last date
30 November 2026
Call for Paper
December Edition
JAAI solicits high quality original research papers for the upcoming December edition of the journal. The last date of research paper submission is 30 November 2026

Submit your paper
Know more
The week's pick
Responsive image
Architecting Behavioural Anomaly Detection for Cloud-Scale Security Operations: An Interpretable Statistical Framework for SOC-Driven Cyber Threat Analytics

Justice Opara-Martins
Reseach Article

An Explainable Machine Learning Framework for Loan Default Prediction in Fintech using Ensemble Learning Models

by Chioma Julia Onwuzo, Godfrey Perfectson Oise, Ifeoma Vivian Ngonadi, Immunhierokene Clinton Obrorindo, Augustine Emakpor Otorokpo
journal cover thumbnail

Journal of Advanced Artificial Intelligence
Foundation of Computer Science (FCS), NY, USA
Volume 2 - Number 7
Year of Publication: 2026
Authors: Chioma Julia Onwuzo, Godfrey Perfectson Oise, Ifeoma Vivian Ngonadi, Immunhierokene Clinton Obrorindo, Augustine Emakpor Otorokpo

Chioma Julia Onwuzo, Godfrey Perfectson Oise, Ifeoma Vivian Ngonadi, Immunhierokene Clinton Obrorindo, Augustine Emakpor Otorokpo . An Explainable Machine Learning Framework for Loan Default Prediction in Fintech using Ensemble Learning Models. Journal of Advanced Artificial Intelligence. 2, 7 ( Oct 2026), 26-35. DOI=None

@article{ None,
author = { Chioma Julia Onwuzo, Godfrey Perfectson Oise, Ifeoma Vivian Ngonadi, Immunhierokene Clinton Obrorindo, Augustine Emakpor Otorokpo },
title = { An Explainable Machine Learning Framework for Loan Default Prediction in Fintech using Ensemble Learning Models },
journal = { Journal of Advanced Artificial Intelligence },
issue_date = { Oct 2026 },
volume = { 2 },
number = { 7 },
month = { Oct },
year = { 2026 },
pages = { 26-35 },
numpages = {9},
url = { https://jaaionline.phdfocus.com/archives/volume2/number7/an-explainable-machine-learning-framework-for-loan-default-prediction-in-fintech-using-ensemble-learning-models/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-10-30T22:21:59.387048+05:30
%A Chioma Julia Onwuzo
%A Godfrey Perfectson Oise
%A Ifeoma Vivian Ngonadi
%A Immunhierokene Clinton Obrorindo
%A Augustine Emakpor Otorokpo
%T An Explainable Machine Learning Framework for Loan Default Prediction in Fintech using Ensemble Learning Models
%J Journal of Advanced Artificial Intelligence
%V 2
%N 7
%P 26-35
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

The rapid expansion of fintech has intensified the need for accurate and transparent models for loan default prediction, which is critical for effective credit risk management. This study proposes an explainable machine learning framework that combines ensemble learning models with explainable artificial intelligence (XAI) techniques to enhance both predictive performance and interpretability. Using the LendingClub dataset, two ensemble models Random Forest and Extreme Gradient Boosting (XGBoost) were developed and evaluated. Model performance was assessed using multiple metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, with particular emphasis on detecting the minority class (loan defaults). The results indicate that both models achieved relatively high overall accuracy of approximately 79%. However, they performed poorly in identifying default cases, as reflected by low recall and F1-scores, highlighting the limitations of accuracy in imbalanced datasets. XGBoost slightly outperformed Random Forest and was selected as the final model, although the performance difference was minimal. To address the interpretability challenge of complex models, SHapley Additive exPlanations (SHAP) was applied to provide both global and local insights into model predictions. The analysis revealed that interest rate and loan amount are the most influential predictors of default, while higher income and credit scores reduce default risk. These findings align with established financial risk principles and enhance transparency in decision-making. The study demonstrates that integrating ensemble learning with explainable AI is promising, but improving minority class detection remains essential for real-world fintech applications.

References
  1. F. Wahab, I. Khan, and S. Sabada, “Credit card default prediction using ML and DL techniques,” Internet of Things and Cyber-Physical Systems, vol. 4, pp. 293–306, Jan. 2024, doi: 10.1016/j.iotcps.2024.09.001.
  2. X. Zhu, Q. Chu, X. Song, P. Hu, and L. Peng, “Explainable prediction of loan default based on machine learning models,” Data Science and Management, vol. 6, no. 3, pp. 123–133, Sep. 2023, doi: 10.1016/j.dsm.2023.04.003.
  3. L. Feng, J. Qi, Y. Liu, and W. Wang, “The spillover effects of the ‘Binance Incident’ on financial markets: A study based on machine learning approach,” Financ. Res. Lett., vol. 71, Jan. 2025, doi: 10.1016/j.frl.2024.106383.
  4. Y. Ma, P. Zhang, S. Duan, and T. Zhang, “Credit default prediction of Chinese real estate listed companies based on explainable machine learning,” Financ. Res. Lett., vol. 58, Dec. 2023, doi: 10.1016/j.frl.2023.104305.
  5. M. A. Arias-Serna, J. J. Quiza-Montealegre, L. F. Móntes-Gómez, L. U. Clavijo, and A. F. Orozco-Duque, “Explainable Machine Learning Models for Credit Rating in Colombian Solidarity Sector Entities,” Journal of Risk and Financial Management, vol. 18, no. 9, Sep. 2025, doi: 10.3390/JRFM18090489.
  6. J. Li, J. Kang, J. Wu, H. Wang, and X. Yang, “Research on credit card default repayment prediction model,” Journal of Finance and Data Science, vol. 10, Dec. 2024, doi: 10.1016/j.jfds.2024.100136.
  7. S. A. Oyedotun et al., “The Role of Internal Audit in Fraud Detection and Prevention: A Multi-Contextual Review and Research Agenda,” Journal of Science Research and Reviews, vol. 2, no. 2, pp. 76–85, May 2025, doi: 10.70882/josrar.2025.v2i2.51.
  8. S. Lin, D. Song, B. Cao, X. Gu, and J. Li, “Credit risk assessment of automobile loans using machine learning-based SHapley Additive exPlanations approach,” Eng. Appl. Artif. Intell., vol. 147, May 2025, doi: 10.1016/j.engappai.2025.110236.
  9. C. Garitta and L. Grassi, “Predicting break-even in FinTech startups as a signal for success,” Financ. Res. Lett., vol. 74, Mar. 2025, doi: 10.1016/j.frl.2024.106735.
  10. H. Li and W. Wu, “Loan default predictability with explainable machine learning,” Financ. Res. Lett., vol. 60, p. 104867, Feb. 2024, doi: 10.1016/J.FRL.2023.104867.
  11. E. A. Raheem, A. M. Dinar, M. A. Mohammed, and B. Al-Attar, “Improving Loan Status Prediction Accuracy with Generative Adversarial Networks: Addressing Data Scarcity and Bias,” Journal of Intelligent Systems and Internet of Things, vol. 13, no. 1, pp. 251–258, 2024, doi: 10.54216/JISIOT.130118.
  12. S. A. Oyedotun et al., “The Role of Internal Audit in Fraud Detection and Prevention: A Multi-Contextual Review and Research Agenda,” Journal of Science Research and Reviews, vol. 2, no. 2, pp. 76–85, May 2025, doi: 10.70882/josrar.2025.v2i2.51.
  13. L. Wang, Z. Yu, J. Ma, X. Chen, and C. Wu, “A Two-Stage Interpretable Model to Explain Classifier in Credit Risk Prediction,” J. Forecast., vol. 44, no. 7, pp. 2132–2150, Nov. 2025, doi: 10.1002/FOR.3288.
  14. M. Ikermane and Y. Rachidi, “Enhancing Financial Decision-Making with Explainable Artificial Intelligence: A Case Study in Credit Risk Assessment,” 2025, pp. 255–261. doi: 10.1007/978-3-031-88304-0_34.
  15. N. B. Unuigbokhai et al., “ADVANCEMENTS IN FEDERATED LEARNING FOR SECURE DATA SHARING IN FINANCIAL SERVICES,” FUDMA JOURNAL OF SCIENCES, vol. 9, no. 5, pp. 80–86, May 2025, doi: 10.33003/fjs-2025-0905-3207.
  16. Y. Filali and H. El Asri, “Explainable Artificial Intelligence in Credit Scoring: A Novel Framework Integrating Decision Trees and LLMs,” 2026, pp. 29–39. doi: 10.1007/978-3-032-07718-9_3.
  17. V. Ravi et al., “Explainable AI (XAI) for Credit Scoring and Loan Approvals,” 2026, pp. 351–368. doi: 10.1007/978-981-96-8998-9_29.
  18. Sarder Abdulla Al Shiam et al., “Credit Risk Prediction Using Explainable AI,” Journal of Business and Management Studies, vol. 6, no. 2, pp. 61–66, Mar. 2024, doi: 10.32996/jbms.2024.6.2.6.
  19. G. F. Bone-Winkel and F. Reichenbach, “Improving credit risk assessment in P2P lending with explainable machine learning survival analysis,” Digit. Finance, vol. 6, no. 3, pp. 501–542, Sep. 2024, doi: 10.1007/s42521-024-00114-3.
  20. A. A. S. Abubakar, “Artificial Intelligence In Financial Decision Systems: Transforming Risk Assessment And Investment Practices In The Era Of Digital Scientific Culture,” Int. J. Environ. Sci., pp. 3472–3483, Jul. 2025, doi: 10.64252/9240es77.
  21. Q. Xu et al., “SHAP-based Interpretable Models for Credit Default Assessment Using Machine Learning,” in 2024 14th International Conference on Software Technology and Engineering (ICSTE), IEEE, Aug. 2024, pp. 213–217. doi: 10.1109/ICSTE63875.2024.00044.
  22. A. Kanaji, S. Mahale, A. Gattani, R. Rai, P. Tawde, and V. Sawant, “Loan Acceptance Prediction and Analysis Using Explainable AI Techniques,” 2026, pp. 175–186. doi: 10.1007/978-981-96-9971-1_12.
  23. G. Oise and S. Konyeha, “Environmental impacts in e-waste management using deep learning,” Discover Artificial Intelligence, vol. 5, no. 1, p. 210, Aug. 2025, doi: 10.1007/s44163-025-00376-9.
  24. Md. M. Islam, A. Sohag, M. Hasan, Md. K. Islam, and Md. N. Sultan, “XAI-Driven Model Explainability and Prediction of P2P Bank Loan Default Network,” 2024, pp. 109–121. doi: 10.1007/978-981-99-8937-9_8.
  25. Mainuddin Adel Rafi, S M Iftekhar Shaboj, Md Kauser Miah, Iftekhar Rasul, Md Redwanul Islam, and Abir Ahmed, “Explainable AI for Credit Risk Assessment: A Data-Driven Approach to Transparent Lending Decisions,” Journal of Economics, Finance and Accounting Studies, vol. 6, no. 1, pp. 108–118, Feb. 2024, doi: 10.32996/jefas.2024.6.1.11.
  26. G. P. Oise et al., “DECENTRALIZED DEEP LEARNING IN HEALTHCARE: ADDRESSING DATA PRIVACY WITH FEDERATED LEARNING,” FUDMA JOURNAL OF SCIENCES, vol. 9, no. 6, pp. 19–26, Jun. 2025, doi: 10.33003/fjs-2025-0906-3714.
  27. X. Zheng, “Ensemble Learning and SHAP-based Interpretability for AI-Driven Credit Risk Assessment in Financial Default Prediction,” in Proceedings of the 2025 6th International Conference on Computer Science and Management Technology, New York, NY, USA: ACM, Dec. 2025, pp. 168–173. doi: 10.1145/3795154.3795180.
  28. B. Cui, “Loan Forecasting Based on Machine Learning and Variable Correlation Analysis,” Applied and Computational Engineering, vol. 107, no. 1, pp. 127–138, Dec. 2024, doi: 10.54254/2755-2721/2024.18131.
  29. Y. Chen, D. Wu, Y. Ren, C. Shao, D. Wang, and Y. Gu, “A sensorless centrifugal pump operation states estimation method based on HSSA-BPNN,” Measurement (Lond)., vol. 237, Sep. 2024, doi: 10.1016/j.measurement.2024.115238.
  30. A. A. Montevechi, R. de C. Miranda, A. L. Medeiros, and J. A. B. Montevechi, “Advancing credit risk modelling with Machine Learning: A comprehensive review of the state-of-the-art,” Eng. Appl. Artif. Intell., vol. 137, p. 109082, Nov. 2024, doi: 10.1016/j.engappai.2024.109082.
  31. J. Černevičienė and A. Kabašinskas, “Explainable artificial intelligence (XAI) in finance: a systematic literature review,” Artif. Intell. Rev., vol. 57, no. 8, p. 216, Jul. 2024, doi: 10.1007/s10462-024-10854-8.
  32. P. E. de Lange, B. Melsom, C. B. Vennerød, and S. Westgaard, “Explainable AI for Credit Assessment in Banks,” Journal of Risk and Financial Management, vol. 15, no. 12, p. 556, Nov. 2022, doi: 10.3390/jrfm15120556.
  33. M. K. Nallakaruppan, B. Balusamy, M. L. Shri, V. Malathi, and S. Bhattacharyya, “An Explainable AI framework for credit evaluation and analysis,” Appl. Soft Comput., vol. 153, p. 111307, Mar. 2024, doi: 10.1016/j.asoc.2024.111307.
  34. E. Kocoglu and T. Ersoz, “Trends and Recommendations in Machine Learning Applications for Credit Risk Prediction,” 2025, pp. 789–812. doi: 10.1007/978-3-031-84873-5_61.
Index Terms

Computer Science
Information Sciences

Keywords

Loan Default Prediction Ensemble Learning Explainable Artificial Intelligence (XAI) SHAP (Shapley Additive Explanations) Credit Risk Assessment

Powered by PhDFocusTM