期刊
EXPERT SYSTEMS WITH APPLICATIONS
卷 36, 期 4, 页码 7611-7616出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.eswa.2008.09.054
关键词
Credit scoring; Support vector machines; Classification and regression tree; Multivariate adaptive regression splines; Credit-risk evaluation
类别
资金
- National Natural Science Foundation of China [70371028]
- National Excellent Youth Fund [70825006]
- Hunan Furong Scholar Programme
Credit scoring has become a critical and challenging management science issue, as the credit industry has been facing fiercer competition in recent years. Many methods have been suggested to tackle this problem in the literature. In this paper, we proposed hybrid support vector machine technique based on three strategies: (1) using CART to select input features, (2) using MARS to select input features, (3) using grid search to optimize model parameters. In order to verify the feasibility and effectiveness of the proposed hybrid SVM model, one credit card dataset provided by a local bank in China is used in this study. Analytic results demonstrate that the hybrid SVM technique not only has the best classification rate, but also has the lowest Type II error in comparison with CART, MARS and SVM and justify the presumptions that SVM having better capability of capturing nonlinear relationship among variables. (C) 2008 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据