The process of effective credit risk assessment plays an important role in the financial decision making in Microfinance Institutions (MFIs) as it enables faster credit approval decisions and diminishes the possible risks associated with customers’ repayment defaults. Credit scoring is the most commonly used technique for evaluating the creditworthiness of loans which has gradually begun to find its way into the microfinance field. Many parametric and nonparametric techniques have been adopted by financial institutions to develop accurate credit scoring models. In this study, a credit scoring model is developed for a Tunisian Microfinance Bank by applying fuzzy classifiers where the fuzzy knowledge bases are optimized through differential evolution. Further, the performance of the proposed model is compared to that of the decision tree model. The obtained results reveal that the proposed model consistently gives a better average correct classification rate than the decision tree model. As with the decision tree model, the proposed model can be easily understood by any user and is very useful in the context of credit evaluation process, since it is in ‘if-then’ rule form; unlike decision tree model, the proposed model does not stay in a black box. In the proposed model, the interpretation of independent variables may provide valuable information for bankers and consumers, especially in explaining why credit applications are rejected.

Repayment of microcredit is one of the most important concerns in microfinance since these institutions lend to poor and low-income borrowers who have no collateral assets. The high repayment rate enables the Microfinance Institutions (MFIs), whether or not they are profit oriented, to charge subsidized and low interest rates, which would reduce the financial cost of credit and reach as many poor people as possible (i.e., depth of outreach). It may also help decrease the dependence on subsidies and gifts from governments and donors, which would help in achieving self-sustainability.

Due to the increasing competition in microcredit market and the rising level of overindebtedness among microentrepreneurs, researchers feel that MFIs have to develop some powerful risk management tools in order to rationalize the credit granting decision and evaluate the financial performance of their clients. One such tool is credit scoring, which involves using what is known from the past to forecast what might take place in the future. It compares known characteristics or facts about the borrowers and loans with similar past cases in order to estimate the potential borrowers’ risk. Although this method is not new for the conventional banking sector, it constitutes an innovation for MFIs. Since the late 1990s, credit scoring has gradually found its way into the microfinance field (Viganò, 1993; Schreiner, 2004; Simbaqueba et al., 2011; and Van et al., 2011).

Financial Risk Management Journal, Credit Scoring Model, Microfinance Institutions (MFIs), Fuzzy Adaptive Network (FAN), Neuro Fuzzy Classification (NEFCLASS), and Neuro-Fuzzy Inference System (ANFIS), Microfinance Bank, Classifier, Optimized, Differential, Evolution, Algorithm.