Credit Scoring Using Information Fusion Technique

Abstract

Banks frequently face massive credit risks, which might lead to opportunities lost or financial losses. Regarding to this, more and more data mining methods are used in bank credit scoring nowadays. However, different data mining methods for classification can produce different results. The aim of this paper is to fuse the different data mining results together to get one better solution by using the information fusion technique. In this study, information fusion technique is used to build the credit scoring models based on data mining methods such as SVM and Logistic regression model. Two real credit scoring data sets of UCI databases are used to demonstrate the effectiveness and feasibility of the method. The results show that the information fusion model has certain validity, reliability and a higher accuracy than those of the two methods obtained separately.