Credit Decision Making process in FinTech Services in Nigeria: An Application of Logistic Regression Credit Scoring
Abstract
A Robust Enterprise Risk Management (ERM) framework is very critical for FinTech sustainability and continuity as it helps to manage potential losses from lending activities. To this end, the objective of this study is to identify the factors influencing credit risk and to examine credit scoring process for credit risk decision making in FinTech companies in Nigeria. Logistic regression-based methodology was employed to improve and optimized the traditional approach of credit risk decision making. The study utilizes secondary data from a FinTech company over three-years, focusing on both corporate and individual clients who have closed loans with varying tenors. Python software was used to process and analyzed the retrieved data and the key predictors impacting loan repayment behaviour are identified. Loan amount, frequency of repayment and number of dependents are strong predictors while marital status, net pay after statutory deductions, disbursement turn-around-time (TAT) and years in service show moderate predictive strength. This study contributes to the literature by demonstrating the effectiveness of logistic regression in improving credit risk assessment models for FinTech companies in Nigeria. The findings emphasize the need for FinTech companies to integrate logistic regression models into credit scoring systems to enhance risk assessment accuracy and business value creation.
References
Adigun, O. (2021). Development of credit scoring models for SMEs in Nigeria. Small Business Economics, 19(2), 201-220.
Akins, T. (2019). The management of loan repayment behavior. Journal of Financial Studies, 34(2), 115-129.
Akram, M., & Hussain, A. (2020). The challenge of non-performing loans: Predicting and managing loan repayment behavior. Financial Management Review, 45(3), 201-216.
Altman, E. I. (1968). Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. The Journal of Finance, 23(4), 589-609.
Beaver, W. H. (2021). Financial ratios as predictors of failure. Journal of Business Research, 15(3), 401-419.
Einav, L., Jenkins, M., & Levin, J. (2018). The adoption of credit scoring and its effects on loan originations, repayment, and defaults. Finance Journal, 56(1), 78-102.
Emile, A. (2021). The role of healthy loan portfolios in maintaining liquidity and profitability. Banking Operations Review, 52(1), 133-149.
Hand, D. J., & Henley, W. E. (1997). Statistical classification methods in consumer credit scoring: a review. Journal of the Royal Statistical Society: Series A (Statistics in Society), 160(3), 523-541.
Khandani, A. E., Kim, A. J., & Lo, A. W. (2020). Consumer credit-risk models via machine-learning algorithms. Journal of Banking & Finance, 34(11), 2767-2787.
Kofi, T. (2017). Extension of credit facilities by Microfinance institutions. Microfinance Journal, 19(3), 110-123.
Lamichhane, B.D. (2022). Loan Delinquency in Microfinance Institutions (MFIs): Ways to Overcome the Problem. Nepalese Journal of Management Research, 2, 37-43
Le, H.N.Q., Nguyen, T.V.H., Schinckus, C., 2022. Bank lending behaviour and macroeconomic factors: A study from strategic interaction perspective. Heliyon ScienceDirect, 8(11) https://doi.org/10.1016/j.heliyon.2022.e11906
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.
Ogunyele, T., & Akanni, O. (2021). Techniques for informed credit decisions in a complex financial landscape. Journal of Credit Risk Analysis, 34(2), 189-205.
Ojeka, S. (2019). The impact of credit scoring models on credit risk management in Nigerian commercial banks. Journal of Risk Management, 12(2), 201-215.
Okafor, C., & Agiomoh, U. (2022). Credit scoring and loan performance in Nigerian banking sector. Journal of Financial Stability, 18(1), 102-120.
Sum, R.M.D., Ismail, W., Abdullah, Z.H., Noor Shah, N.F. and Hendradi, R. (2022). A New Efficient Credit Scoring Model for Personal Loan Using Data Mining Technique Toward for Sustainability Management. Journal of Sustainability Science and Management, 17(5), 60-76.
Thomas, J. (2021). Credit scoring and its applications. International Journal of Finance & Economics, 28(4), 512-530.
