Credit Risk Assessment in Microfinance Institutions Through Scoring: Moroccan Case
Microfinance institutions are organizations that provide financial services to people who are poor or excluded from the financial system. However, they often face many difficulties, such as non-repayment of loans by borrowers. In developing countries like Morocco, this situation has led to the failure of several microcredit institutions.
Before granting such loans, MFIs face difficulties in assessing the riskiness of potential borrowers. In this context, efficient instruments are needed to assess credit risk,
The credit scoring model is a mathematical model used to estimate the probability of default, i.e., the likelihood that customers will trigger a credit event (i.e., bankruptcy, bond default, payment default, and cross-default events).
The effectiveness of scoring depends not so much on the technical tools used as in the systematic training of users, credit officers and branch managers will only be convinced that scoring can help them make decisions if they understand how it works and can observe it in concrete tests. This paper describes how credit scoring works, what microcredit institutions can expect from it and how they can use it, as well as the data required.
An empirical study was conducted in 1021 borrowers of a Moroccan microfinance institution, in order to show the predictive capacity of credit scoring models and to identify the explanatory variables of the probability of default of loans granted by MFIs, using a logistic regression model. The results obtained show that the main variables in this regard are the amount of the loan, the number of arrears, the collateral provided, the credit analyst's assessment, the borrower's male gender and the level and trend of the general stock market index. The results presented advance the results of previous research and may be useful to MFI managers, regulatory institutions, financial analysts, and academic researchers.
JEL Classification: G2, G3, C58
Paper type: Empirical research
Copyright (c) 2021 Loubna Assairh, Mohammed Kaicer, Mounir Jerry
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.