The Influence of Days Past Due, Loan Amount, and Deposit Proportion on Non-Performing Loans at the CU Sejahtera Makmur Bersama Savings and Loan Cooperative
DOI:
https://doi.org/10.70550/ecif.v3i1.235Keywords:
Credit Union, Non-performing Loans, Machine Learning, Credit Risk, Financial InclusionAbstract
Credit unions play a crucial role in promoting financial inclusion, yet their sustainability is often threatened by rising non-performing loans (NPLs). This study aims to analyze the influence of Days Past Due, Loan Amount, and Savings Proportion on credit defaults within CU Sejahtera Makmur Bersama, using a comparative machine learning approach. Two ensemble models, Random Forest and XGBoost, were applied to predict the likelihood of credit delinquency. Model performance was evaluated using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the Coefficient of Determination (R²). The results show that XGBoost_Optimized achieved the best overall performance, with the lowest MSE (23,124,275,951) and the highest R² (0.020977), indicating a slightly stronger predictive ability compared to Random Forest, which performed better in terms of MAE (69,923,891). Despite these results, both models exhibited limited explanatory power, suggesting that the selected financial predictors alone cannot capture the complexity of NPL behavior. Therefore, future research is encouraged to incorporate non-financial and behavioral variables, such as borrower characteristics and macroeconomic conditions, as well as alternative modeling techniques like binary classification or unsupervised learning for risk segmentation. These improvements are expected to enhance model accuracy and practical applicability in cooperative credit risk management
Downloads
References
Abdullah, M., Chowdhury, M. A. F., Uddin, A., & Moudud-Ul-Huq, S. (2023). Forecasting nonperforming loans using machine learning. Journal of Forecasting, 42(7), 1664–1689. https://doi.org/10.1002/for.2977
Alvi, J., Arif, I., & Nizam, K. (2024). Advancing financial resilience: A systematic review of default prediction models and future directions in credit risk management. Heliyon, 10(21), e39770. https://doi.org/10.1016/j.heliyon.2024.e39770
Anakpo, G., Mishi, S., Tshabalala, N., & Mushonga, F. B. (2024). Sustainability of credit union: A systematic review of measurement and determinants. Journal of African Business, 25(3), 509–530. https://doi.org/10.1080/15228916.2023.2185423
Atichasari, A. S., Ratnasari, A., Kulsum, U., Kahpi, H. S., Wulandari, S. S., & Marfu, A. (2023). Examining non-performing loans on corporate financial sustainability: Evidence from Indonesia. Sustainable Futures, 6, 100137. https://doi.org/10.1016/j.sftr.2023.100137
Bitetto, A., Cerchiello, P., Filomeni, S., Tanda, A., & Tarantino, B. (2024). Can we trust machine learning to predict the credit risk of small businesses? Review of Quantitative Finance and Accounting, 63, 925–954. https://doi.org/10.1007/s11156-024-01278-0
Boachie, C., & Adu-Darko, E. A. (2022). Ghana: Susu, village savings and loans, credit union, rotating savings system. In Transforming Africa: How Savings Groups Foster Financial Inclusion, Resilience and Economic Development. Emerald Publishing. https://doi.org/10.1108/978-1-80262-053-520221011
Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
Carrera-Silva, K., Rodríguez Ulcuango, O. M., Abdo-Peralta, P., Castelo Salazar, Á. G., Samaniego Erazo, C. A., & Haro Ávalos, D. (2024). Beyond the financial horizon: A critical review of social responsibility in Latin American credit unions. Sustainability, 16(18), 7908. https://doi.org/10.3390/su16187908
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
Černevičienė, J., & Kabašinskas, A. (2024). Explainable artificial intelligence (XAI) in finance: A systematic literature review. Artificial Intelligence Review, 57, 216. https://doi.org/10.1007/s10462-024-10854-8
Gambacorta, L., Huang, Y., Qiu, H., & Wang, J. (2024). How do machine learning and non-traditional data affect credit scoring? New evidence from a Chinese fintech firm. Journal of Financial Stability, 73, 101284. https://doi.org/10.1016/j.jfs.2024.101284
Goyal, S., Singhal, N., Mishra, N., & Verma, S. K. (2023). The impact of macroeconomic and institutional environment on NPL of developing and developed countries. Future Business Journal, 9, 45. https://doi.org/10.1186/s43093-023-00216-1
Islamic Financial Services Board. (2015). Core Principles for Islamic Finance Regulation (Banking Segment) (IFSB-17). https://www.ifsb.org/
Kaufman, S., Rosset, S., Perlich, C., & Stitelman, O. (2012). Leakage in data mining: Formulation, detection, and avoidance. ACM Transactions on Knowledge Discovery from Data, 6(4), Article 15. https://doi.org/10.1145/2382577.2382579
Khandani, A. E., Kim, A. J., & Lo, A. W. (2010). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767–2787. https://doi.org/10.1016/j.jbankfin.2010.06.001
Lessmann, S., Baesens, B., Seow, H.-V., & Thomas, L. C. (2015). Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1), 124–136. https://doi.org/10.1016/j.ejor.2015.05.030
Lisa, O., Nugroho, L., Orban, I., Utami, W., & Nugraha, E. (2023). The performance of Islamic microfinance institutions in the COVID-19 pandemic: Is asset quality important? Sosyoekonomi, 31(58), 145–160. https://doi.org/10.17233/sosyoekonomi.2023.04.07
Martins, P., Pinheiro de Lima, E., Bortoluzzi, S. C., & Gouvea da Costa, S. E. (2021). Performance assessment of the operations strategy of credit unions. International Journal of Productivity and Performance Management, 72(1), 109–136. https://doi.org/10.1108/IJPPM-10-2020-0521
Naz, F., Lutfullah, T., Pervaiz, S., & Ahmad, M. I. (2024). Factors influencing loan delinquency in microfinance institutions: A literature review. In Microfinance: Interventions in Challenging Contexts (pp. 75–90). Springer. https://doi.org/10.1007/978-981-97-5388-8_5
Nugroho, L., Villaroel, W., & Utami, W. (2018). The challenges of bad debt monitoring practices in Islamic micro banking. European Journal of Islamic Finance, (11). https://doi.org/10.13135/2421-2172/2758
Nwafor, C. N., & Nwafor, O. Z. (2023). Determinants of non-performing loans: An explainable ensemble and deep neural network approach. Finance Research Letters, 56, 104084. https://doi.org/10.1016/j.frl.2023.104084
Xu, Q., Liu, C., Luo, J., & Liu, F. (2024). Using machine learning to investigate the determinants of loan default in P2P lending: Are there differences between before and during COVID-19? Pacific-Basin Finance Journal, 102550. https://doi.org/10.1016/j.pacfin.2024.102550
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Economics & Islamic Finance Journal (ECIF)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
