A comparative study of discrimination methods for credit scoring

Credit scoring has become an important management science issue as the credit industry has been experiencing enormous growth during the past few decades. Numerous popular classification methods (e.g. linear discriminant analysis, quadratic discriminant analysis, and logistic regression) have been applied in credit scoring for years. Recently researchers proposed several sophisticated and highly effective data mining techniques, such as Skew-normal discriminant analysis (SNDA), Skew-t discriminant analysis (STDA), Stepwise discriminant analysis (SDA), Sparse discriminant analysis (Sparse DA), Flexible discriminant analysis (FDA), and Mixture discriminant analysis (MDA). The objective of this study is to examine these recently proposed discrimination methods for screening credit applicants. The performance of various credit scoring models is evaluated by one real-world credit scoring dataset. The predictive ability of each credit scoring model is accessed by the total percentage of correctly classified cases (total PCC) and the bad rate among accepts (BRA). The results show that SNDA, STDA, and SDA are outperforming techniques for implementing credit scoring models.