Prototyping a Credit Scoring Model for Micro Finance Institutions in Kenya: A Case of Kenya Women Fund Trust (KWFT) Bank
Abstract
Credit scoring models are measurable examination utilized by credit authorities to assess your value to get credit. It breaks down the attributes and characteristics of past loans to foresee the performance of future loans. The KWFT client fits the demographic profile of a woman of the age between 25 to 60 years old. Given that for the KWFT client base, much of their financial information is limited and therefore judgmental and group security approach is mainly used. The study sought to prototype a behavioral credit scoring model that predicts the probability of defaulting on loan payments. The system for building the credit scoring models included the accompanying procedure which entailed ‘performers’ and ‘defaulters’. The target population was 800,000 clients spread across 230 branches. The study used data of 20 best credit performing clients and 20 poor performing clients in all branches in Nairobi County and environs. A total of 480 clients were therefore sampled. Modeling techniques used was logistic regression. The study involved the delivery of a software based prototype. Findings indicated that the odds of defaulting was 1.497 times greater for males as opposed to females and the relation was significant, all classes of age were not significant determinant of performance rating. The study established that individual unmarried was highly likely to default as opposed to individual married, the relation however is insignificant. Group membership was found to greatly predict the rate of default. The study concluded that defaulting was based on information, and in microfinance, this information was usually qualitative and informal and resides with group members or with loan officers. It was recommended that senior management should see the strategic value in developing, implementing, and using scorecards as an integral approach to managing risk within microfinance.
Keywords: Credit scoring, Prototype, Defaulting, performing and Microfinance
References
Blake, C.L., & C.J. Merz. (1998).UCI repository of machine learning databases [http://www.ics.uci.edu/~mlearn/MLRepository.html], University of California, Department of Information and Computer Science.
Business Banking Board (2000). Credit Scoring for High-end Small Business Customers.
Caire, D., & Kossman, R. S. (2003). Credit Scoring: Is It Right for Your Bank? In Bannock Consulting, Credit Risk Conference.
Cundiff, K. (2004). Closing the loop: How credit scoring drives performance improvements along the financial value chain, Business Credit 106(3) 38-42.
Diana, T. (2005). Credit risk analysis and credit scoring – now and in the future, Business Credit 107(3) 12-16.
Lahsasna, A. Ainon, R.N. and Wah, T.Y., 2010.Credit Scoring Models Using Soft Computing Methods: A Survey. The International Arab Journal of Information Technology, 7(2) pp.116-122.
Littwin, A. (2007). Beyond usury: A study of credit-card use and preference among low-income consumers. Tex. L. Rev., 86, 451.
Stein (2001). Peer. Making Small Business Finance Profitable. Proceedings from the Global Conference on Credit Scoring, Washington, D.C.
Thomas, L.C. (2000). A survey of credit and behavioral scoring – forecasting financial risk of lending to consumers, International Journal of Forecasting 16(2) 163-167
