Machine Learning Adoption and its Effect on Efficiency of Credit Analysis in Tier II Commercial Banks in Kenya
DOI:
https://doi.org/10.47941/ijf.3357Keywords:
Regulatory Pressure, Technological Readiness, Organizational Capacity, Efficiency of Credit AnalysisAbstract
Purpose: The purpose of the study was to examine the Machine Learning Adoption and its Effect on Efficiency of Credit Analysis in Tier II Commercial Banks in Kenya. The study specifically aimed at assessing the effect of regulatory pressure, technological readiness and organizational capacity on efficiency of Credit Analysis.
Methodology: The study adopted a descriptive research design, targeting 48 professionals comprising of credit risk managers, data analysts, loan officers, IT officers, compliance officers, and strategy leads through census sampling technique. Primary data was collected through structured questionnaires using 5-point Likert scales. Data analysis was conducted using SPSS version 28.0, employing both descriptive statistics and inferential statistics.
Findings: Regarding the first objective, results revealed a statistically significant strong positive relationship between regulatory pressure and efficiency of credit analysis, r (48) = 0.616, p < .05. Multiple regression analysis indicated that regulatory pressure explained 37.9% of variance in credit analysis efficiency, R² = 0.379, F (1, 46) = 28.059, p < .05, β = 0.616, p < .05. For the second objective, findings indicated a statistically significant very strong positive relationship between technological readiness and efficiency of credit analysis, r (48) = 0.819, p < .05. Regression analysis showed that technological readiness explained 67.0% of variance in credit analysis efficiency, R² = 0.670, F (1, 46) = 93.375, p < .05, β = 0.819, p < .05. Regarding the third objective, results showed a statistically significant very strong positive relationship between organizational capacity and efficiency of credit analysis, r (48) = 0.803, p < .05. Multiple regression analysis indicated that organizational capacity explained 64.5% of variance in credit analysis efficiency, R² = 0.645, F (1, 46) = 83.527, p < .05, β = 0.803, p < .05.
Unique Contribution to Theory, Practice and Policy: The study recommended that the Central Bank of Kenya should continue refining regulatory frameworks that encourage machine learning adoption. Tier II banks should prioritize systematic investments in digital infrastructure, exploring cloud-based solutions, investing in data quality improvement initiatives, and strengthening cybersecurity frameworks. Banks should also invest systematically in human capital development through competitive recruitment strategies, comprehensive training programs, leadership development, and cultural transformation initiatives.
Downloads
References
Addo, P. M., Guegan, D., & Hassani, B. (2018). Credit Analysis using machine and deep learning models. Risks, 6(2), 38.
Addy, W. A., Ugochukwu, C. E., Oyewole, A. T., Ofodile, O. C., Adeoye, O. B., & Okoye, C. C. (2024). Predictive analytics in credit risk management for banks: A comprehensive review. GSC Advanced Research and Reviews, 18(2), 434--449.
Al Zaidanin, J. S., & Al Zaidanin, O. J. (2021). The impact of credit risk management on the financial performance of United Arab Emirates commercial banks. International Journal of Research in Business and Social Science, 10(3), 303--319.
Baker, J. (2011). The technology--organization--environment framework. Information Systems Theory: Explaining and Predicting Our Digital Society, Vol. 1, 231-245.
Central Bank of Kenya. (2023). Survey on Artificial Intelligence in the Banking Sector. https://www.centralbank.go.ke
Central Bank of Kenya (2023) Bank Supervision Annual Report 2023. CBK
Creswell, J. W., & Creswell, J. D. (2018). Research design: Qualitative, quantitative, and mixed methods approaches (5th ed.). SAGE Publications.
Edunjobi, T. E., & Odejide, O. A. (2024). Theoretical frameworks in AI for credit risk assessment: Towards banking efficiency and accuracy. International Journal of Scientific Research Updates, 7(01), 092-102.
Gasmi, I., Neji, S., Mansouri, N., & Soui, M. (2025). Bank credit risk prediction using machine learning model. Neural Computing and Applications, 1-18.
Gatla, T. R. (2023). Machine Learning in Credit Risk Assessment: Analyzing How Machine Learning Models Are. International Journal of Emerging Technologies and Innovative Research, 6(7), 4-8.
Hegde, S. K., Hegde, R., Marthanda, A. V. G. A., & Logu, K. (2023, February). Performance analysis of machine learning algorithm for the Credit Analysis in the banking sector. In 2023 7th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 57-63). IEEE.
Kanyambu, F. M. (2021). A system dynamics model for credit risk modelling and simulation: The case of licensed credit reference bureaus in Kenya (Doctoral dissertation, KCA University).
Karanja, J. G. (2019). Credit risk and lending performance of commercial banks in Kenya (Doctoral dissertation, KeMU).
Kimani, J., & Kibera, M. (2023). Evolution of risks facing commercial banks in Kenya and associated strategic responses. International Journal of Modern Risk Management, 1(2), 56-65.
Leo, M., Sharma, S., & Maddulety, K. (2019). Machine learning in banking risk management: A literature review. Risks, 7(1), 29.
Mulwa, M. M., & Yahya, U. (2025). Review of digital lending models for financial inclusion: Challenges, opportunities, and way forward. European Journal of Business and Management Research, 10(2), 184-191.
Murugan, M. S. (2023). Large-scale data-driven financial risk management & analysis using machine learning strategies. Measurement: Sensors, 27, 100756.
Mutembete, M. B. (2022). Credit Risk Assessment Model Using Machine Learning (Doctoral dissertation, KCA University).
Nkambule, D. S., Twala, B., & Pretorius, J. H. C. (2024). Effective machine learning techniques for dealing with poor credit data. Risks, 12(11), 172.
Nyangena, B. O. (2019). Consumer credit risk modelling using machine learning algorithms: a comparative approach (Doctoral dissertation, Strathmore University).
Parasuraman, A. (2000). Technology Readiness Index (TRI): A multiple-item scale to measure readiness to embrace new technologies. Journal of Service Research, 2(4), 307-320.
Rogers, E. M. (2003). Diffusion of innovations (5th ed.). Free Press.
Shi, S., Tse, R., Luo, W., D'Addona, S., & Pau, G. (2022). Machine learning-driven credit risk: a systemic review. Neural Computing and Applications, 34(17), 14327-14339.
Sriram, H. K. (2025). Leveraging artificial intelligence and machine learning for next-generation credit risk assessment models. European Advanced Journal for Science & Engineering (EAJSE)-p-ISSN 3050-9696 en e-ISSN 3050-970X, 3(1).
Tornatzky, L. G., & Fleischer, M. (1990). The processes of technological innovation. Lexington Books.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Catherine Muthuuri, Prof. Allan Kihara
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution (CC-BY) 4.0 License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
