Study of Multi-Class SVMs on the Credit Assessment of Electricity Customers

摘要：

According to the research statues quo of the credit assessment of electricity customers, it can be classified the credit of electricity customers for four classes by means of the credit assessment criterions of commercial banks. We combine the Multi-class Support Vector Machines (Multi-class SVM) and binary tree to establish the assessing model. And a real case is given and BP neural network is also used to assess the same data. In order to verify the effectiveness of the method, the experiment results show that Multi-class SVM classifier is more effective in the credit assessment of electricity customers and achieves better performance than BP network.

作者: Jianguo Zhou Xiaowei Wang

作者单位: Department of Business Administration North China Electric Power University Baoding, 071003, P.R.Chi Department of Business Administration North China Electric Power University Baoding, 071003,P.R. Chi

会议类型: 国际会议

会议名称: Fourth International Conference on Impulsive and Hybrid Dynamical Systems(ICIHDS 2007)(第四届国际脉冲和混合动力系统学术会议)

会议地点: 南宁

会议语种:英文

在线出版日期: 2007-07-20（万方平台首次上网日期，不代表论文的发表时间）