Applications of classification trees to consumer credit scoring methods in commercial banks

扫码查看

原文链接

NETL

外文摘要：Based on the theory of classification trees， the samples that are taken out from one commercial bank of China are put into classification tree models。 When comparing results of models， it is considered that the model size， the structure of the sample and error cost could influence model's error rates。 The optimized classification tree model is produced out based on the comparisons。 It is concluded that classification trees are more suitable than logistic regression for present domestic credit scoring because of characters of the samples， through comparing classification trees and logistic regression。

外文关键词：

optimisationtrees (mathematics)pattern classificationbankingcredit transactionscommercial banksconsumer credit scoring methodsclassification treesdomestic credit scoringlogistic regressionpersonal credit

作者：

Xiu Li、Weiyun Ying、Jianyong Tuo、Bing Li、Wenhuang Liu

展开 >

作者单位：

Res. Center of CIMS, Tsinghua Univ., Beijing, China

会议母体文献：

Systems, Man and Cybernetics, 2004 IEEE International Conference on

页码：

p.4112-4117

出版时间：

2004

DOI：

10.1109/ICSMC.2004.1401175