多种个人信用评分模型在中国应用的比较研究  

The Comparative Analysis of the Application of Several Scoring Models of Consumer Credit in China

作　　者：石庆焱 靳云汇[1] 

机构地区：[1]北京大学光华管理学院

出　　处：《统计研究》2004年第6期43-47,共5页Statistical Research

摘　　要：Based on a set of credit card sample of Chinese commercial bank,a systemically comparative study of various statistical credit scoring models was firstly made in China The comparative study indicated that every model has its own strength and weakness The strengths of linear discriminant analysis,linear program,and Logistic regression are that these models are explainable and their outputs can be a linear scorecard(so can be easily implemented) But these models have higher misclassification rate comparing with others Neural network and classification tree models have a higher predict accuracy,but may be‘over fitted’,and their outputs are hard to beBased on a set of credit card sample of Chinese commercial bank,a systemically comparative study of various statistical credit scoring models was firstly made in China The comparative study indicated that every model has its own strength and weakness The strengths of linear discriminant analysis,linear program,and Logistic regression are that these models are explainable and their outputs can be a linear scorecard(so can be easily implemented) But these models have higher misclassification rate comparing with others Neural network and classification tree models have a higher predict accuracy,but may be‘over fitted’,and their outputs are hard to be explained

关 键 词：个人信用 评分模型 中国 比较研究 LOGISTIC回归 神经网络 

分 类 号：F832.479[经济管理—金融学] B82-053[哲学宗教—伦理学]