Strategic Integration of Predictive Analytics and Loan Portfolio Quality in Deposit-Taking SACCOs in Kenya
Abstract
The study examined the relationships between predictive analytics practices and loan portfolio quality in Kenyan deposit-taking SACCOs and whether organizational readiness moderated these relationships. A longitudinal explanatory design used secondary institutional data for 2021–2024. Of 176 licensed DT-SACCOs, 164 had complete records. Descriptive analysis and panel regression examined data-driven risk assessment, credit scoring, predictive monitoring and interactions with organizational readiness. The moderated model reported negative coefficients for risk assessment (B = −0.185), credit scoring (B = −0.220) and predictive monitoring (B = −0.295). The corresponding interaction coefficients were −0.095, −0.112 and −0.145. The reported model-summary table showed R² increasing from 0.685 to 0.796. Data management capacity may strengthen the association between analytics-related credit practices and improved loan portfolio outcomes. The study recommends that SACCO boards and regulators should emphasize reliable data, credit model oversight and early-warning monitoring. The results describe associations, not causal effects, and statistical outputs require verification against the original analysis.
Keywords: Organizational Readiness, Data Management, Credit Risk, Predictive Monitoring, Deposit-Taking SACCOs
References
Ally, O. J., Kulindwa, Y. J., & Mataba, L. (2025). Financial technology and credit risk management: the case of non-performing loans in Tanzanian banks. Cogent Economics & Finance, 13. https://doi.org/10.1080/23322039.2025.2459188
Berhane, T., Melese, T., & Seid, A. M. (2024). Performance Evaluation of Hybrid Machine Learning Algorithms for Online Lending Credit Risk Prediction. Applied Artificial Intelligence, 38. https://doi.org/10.1080/08839514.2024.2358661
Chang, V., Xu, Q. A., Akinloye, S. H., Benson, V., & Hall, K. (2025). Prediction of Bank Credit Worthiness Through Credit Risk Analysis: An Explainable Machine Learning Study. Annals of Operations Research, 354, 247–271.
Etenyi, P. H., Nelima, M., & Maingi, M. (2024). Effect of Credit Risk Management Techniques on Financial Performance of Deposit Taking SACCOs in Kenya. African Journal of Empirical Research.
Gafsi, M. (2025). Machine learning applications in banking: A comparative analysis of Random Forest and XGBoost in credit default forecasting. Journal of Financial Data Science, 7(1), 45–62. https://doi.org/10.2139/ssrn.4082194
Hahami, E., & Piper (2022). A Meta-Analysis Evaluating the Performance of Machine Learning Models on Probability of Loan Default. Journal of Student Research, 11(2). DOI: 10.47611/jsrhs.v11i2.2726
Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (3rd ed.). Guilford Press.
Hussain, M., & Papastathopoulos, A. (2022). Organizational readiness for digital financial innovation and financial resilience. International Journal of Production Economics, 243, 108326. DOI: 10.1016/j.ijpe.2021.108326
International Monetary Fund. (2021). Financial soundness indicators: Compilation guide. Washington, DC: IMF.
Jagtiani, J., & Lemieux, C. (2019). The roles of alternative data and machine learning in fintech lending: Evidence from the Lending Club consumer platform. Financial Management, 48(4), 1009–1029. https://doi.org/10.1111/fima.12299
Juma, S. O. (2022). Relevance of alternative data and machine learning in predicting default in a non-deposit taking SACCO in Kenya [Master’s thesis, Strathmore University]. Strathmore University Repository.
Kaffenberger, M., Totolo, E., & Soursourian, M. (2022). A Digital Credit Revolution: Insights from Kenya's Digital Lending Market.
Kumar, G., Rahman, M. R., Rajverma, A., & Misra, A. K. (2023). Predicting systemic risk of banks: a machine learning approach. Journal of Modelling in Management, 19, 441–469. https://doi.org/10.1108/jm2-12-2022-0288
Liu, J., Zhang, X., & Xiong, H. (2024). Credit Risk Prediction Based on Causal Machine Learning: Bayesian Network Learning, Default Inference, and Interpretation. Journal of Forecasting, 43(5), 1625–1660.
Marimo, M., & Chimedza, C. (2022). SME credit risk modelling in South Africa: A case study. Acta Economica, 20(36). DOI: 10.7251/ace2236009m
Matenda, F.R., & Sibanda, M. (2025). Default risk modelling for small-to-medium enterprises in the context of stressed conditions in an undeveloped economy. Afro-Asian Journal of Finance and Accounting, 15(5), 590–621.
Mazimpaka, J., & Nizeyimana, P. (2025). Machine learning in cooperative financial societies: Predicting risk through behavioral patterns.
Mutuku, L. M., Maina, K. E., & Matanda, J. W. (2025). Credit Risk Management and Asset Quality of Tier One Deposit-Taking SACCOs in Nairobi, Kenya. International Journal of Finance.
Muturi, W., & Omagwa, J. (2022). Loan Portfolio Quality and Financial Sustainability of Deposit-Taking SACCOs in Kenya.
Mwalozi, J. (2023). Machine learning models in credit risk management: Application in DT-SACCO loan data.
Nalini, R., & Viswadhanush, B. R. (2025). Predictive Analytics and Feature Importance in Financial Decision-Making: Focus on Loan Approval and Risk Assessment. Global Business Review.
Ngugi, B., & Muriithi, J. (2021). Digital Financial Services and Credit Risk Management in Kenya.
Okeyo, N. A., Odoyo, F., & Omboi, B. (2023). Influence of loan loss provisioning ratio prudential regulations on financial performance of deposit taking Savings and Credit DT-SACCOs in Kenya. The University Journal, 5(3), 77–90. https://doi.org/10.59952/tuj.v5i3.258
Pang, S.L., Wei, M., Yuan, J.M., Zhu, B.Z., & Wen, Z.M. (2021). WT combined early warning model and applications for loaning platform customers' default prediction in smart city. Journal of Ambient Intelligence and Humanized Computing. DOI: 10.1007/s12652-021-03166-0
Republic of Kenya. (2010). The Sacco Societies (Deposit-Taking Sacco Business) Regulations, 2010 (Legal Notice No. 95 of 2010).
Rizvi, S.I., Usman, M., Bashir, Z., Iqbal, S., & Rao, Z. (2025). Assessing the Impact of Organizational Readiness and Digital Financial Innovation on Financial Resilience: Evidence from Banking Sector of an Emerging Economy. Jinnah Business Review, 13(1), 36–49. DOI: 10.53369/UOPQ7259
Roy, P. K., & Shaw, K. (2021). A multicriteria credit scoring model for SMEs using hybrid BWM and TOPSIS. Financial Innovation, 7. https://doi.org/10.1186/s40854-021-00295-5
Sacco Societies Regulatory Authority. (2024). SACCO supervision annual report 2024.
Sacco Societies Regulatory Authority. (2023). DT-SACCO supervision annual report, 2023. https://www.sasra.go.ke/2023/08/28/DT-SACCO-supervision-annual-report-2023/
Sacco Societies Regulatory Authority. (2024). The DT-SACCO annual supervision report 2023. SASRA. https://www.sasra.go.ke/
Sadok, H., Sakka, F., & El Maknouzi, M. E. H. (2022). Artificial intelligence and bank credit analysis: A review. Cogent Economics & Finance, 10. https://doi.org/10.1080/23322039.2021.2023262
Samitas, A., Kampouris, E., & Kenourgios, D. (2020). Machine learning as an early warning system to predict financial crisis. International Review of Financial Analysis, 71, 101507. DOI: 10.1016/j.irfa.2020.101507
SAS Institute. (2020). Predictive analytics: What it is and why it matters. Cary, NC: SAS Institute Inc.
World Bank. (2021). Managing risk and creating value with microfinance: Portfolio quality indicators for savings and credit DT-SACCOs.
Zhang, X., Zhang, T., Hou, L., Liu, X., Guo, Z., Tian, Y., & Liu, Y. (2025). Data-driven loan default prediction: A machine learning approach for enhancing business process management.
Zhu, L., Qiu, D., Ergu, D., Ying, C., & Liu, K. (2019). A study on predicting loan default based on the random forest algorithm. Procedia Computer Science, 162, 503–513. DOI: 10.1016/j.procs.2019.12.017
