A Bi-Level Neural-Based Fuzzy Classification Approach for Credit Scoring Problems MEHDI KHASHEI,* MOHAMMAD TAGHI REZVAN, ALI ZEINAL HAMADANI, AND MEHDI BIJARI Department of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran Received 6 April 2013; Revised 2 June 2013; accepted 26 June 2013 The credit scoring is a risk evaluation task considered as a critical decision for financial institutions in order to avoid wrong decision that may result in huge amount of losses. Classification models are one of the most widely used groups of data mining approaches that greatly help decision makers and managers to reduce their credit risk of granting credits to customers instead of intuitive experience or portfolio management. Accuracy is one of the most important criteria in order to choose a credit-scoring model; and hence, the researches directed at improving upon the effectiveness of credit scoring models have never been stopped. In this article, a hybrid binary classification model, namely FMLP, is proposed for credit scoring, based on the basic concepts of fuzzy logic and artificial neural networks (ANNs). In the proposed model, instead of crisp weights and biases, used in traditional multilayer percep- trons (MLPs), fuzzy numbers are used in order to better model of the uncertainties and complexities in financial data sets. Empirical results of three well-known benchmark credit data sets indicate that hybrid proposed model outperforms its component and also other those classification models such as support vector machines (SVMs), K- nearest neighbor (KNN), quadratic discriminant analysis (QDA), and linear discriminant analysis (LDA). Therefore, it can be concluded that the proposed model can be an appropriate alternative tool for financial binary classifica- tion problems, especially in high uncertainty conditions. V C 2013 Wiley Periodicals, Inc. Complexity 18: 46–57, 2013 Key Words: classification; fuzzy logic and fuzzy models; artificial neural networks (ANNs); multilayer percep- trons (MLPs); credit scoring 1. INTRODUCTION O ne of the most important tasks in financial institu- tions is to develop the set of models and techniques that enable to score credit [1]. Credit scoring, defined by Lewis, 1994 [2], is ‘‘any of the many forms of commerce under which an individual obtains money or goods or services on condition of a promise to repay the money or Correspondence to: Mehdi Khashei, Department of Industrial Engineering, Isfahan University of Technology, Isfahan, Iran. E-mail: Khashei@in.iut.ac.ir Contract grant sponsor: Industrial Engineering Department, Isfahan University of Technology 46 COMPLEXITY Q2013 Wiley Periodicals, Inc., Vol. 18 No. 6 DOI 10.1002/cplx.21458 Published online 30 July 2013 in Wiley Online Library (wileyonlinelibrary.com)