The integrated methodology of rough set theory and fuzzy SVM for customer classification

In this paper, an intelligent system that hybridized rough set approach (RS) and fuzzy support vector machine (FSVM) is applied to the study of customer classification in commercial banks. We can get reduced information table, which implies that the number of evaluation criteria such as financial ratios and qualitative variables is reduced with no information loss through rough set approach. And then, this reduced information table is used to develop classification rules and train FSVM. The rationale of our hybrid system is using rules developed by rough sets for an object that matches any of the rules and FSVM for one that dose not match any of them. By applying the proposed approach to customer classification of China Construction Bank, RS-FSVM not only provides satisfactory approximation and generalization property, but also achieves superior performance to traditional discriminant analysis model (DA), BP neural networks (BPN) and standard SVM.