Application of BP Neural Network Model Based on Rough Set in Personal Housing Loans Credit Scoring

摘要：

With the rapid growth of housing loans in China, personal credit risk has become a crucial problem for commercial banks, which calls for better credit scoring models with greater accuracy. In this paper, the method of Rough Set is used to retreat the customer data of housing loans, so that the evaluation indicators are simplified. The simplified data are then used in the training and testing of the BP neural network model. Comparison of the results shows that the model based on Rough Set is better than traditional BP neural networks models in either total or Type II misclassification rate, which represents its advantage in the practice of personal housing loans credit scoring for commercial banks.

关键词： credit scoring rough sets BP neural networks

作者: JIANG Minghui XIAO Kaizhen LI Rui

作者单位: Department of Applied Economics, Harbin Institute ofTechnology, Harbin, China 150001 Department of C Applied Economics, HarbinInstitute of Technology, Harbin, China 150001 Department of C Applied Economics, Harbin Institute of Technology, Harbin, China 150001

会议类型: 国际会议

会议名称: 2009 International Conference on Construction & Real Estate Management(2009建设与房地产管理国际会议)

会议地点: 北京

会议语种:英文

页码: 969-972

在线出版日期: 2009-11-05（万方平台首次上网日期，不代表论文的发表时间）