基于支持向量机集成的电子商务环境下客户信用评估模型研究  

Study of Customer Credit Evaluation under E-Environment Based on Support Vector Machines Ensemble

作　　者：吴冲[1] 夏晗[1] 

机构地区：[1]哈尔滨工业大学管理学院,黑龙江哈尔滨150001

出　　处：《中国管理科学》2008年第S1期362-367,共6页Chinese Journal of Management Science

基　　金：国家自然科学基金资助项目(70773029);国家教育部博士点基金资助项目(20050213037);哈尔滨工业大学技术政策管理国家哲学社会科学创新基地资助;黑龙江省青年科学基金资助项目(QC04C25)

摘　　要：随着电子商务的快速发展,越来越多的顾客参与到电子商务中来,目前国内电子商务相关的配套设施、法律法规等均不完善,信用问题是困扰电子商务发展的主要瓶颈问题,而客户信用评估是电子商务的重要组成部分,本文利用基于模糊积分的支持向量机集成方法对客户信用进行评估,该方法考虑了各子分类器的分类结果和各子分类器判决对最终决策的重要程度。通过实证分析探讨了此法的可行性和优越性,为我国建立电子商务客户评价体系提供参考。As the rapid development of electronic commerce,there are increasing online customers.However matching establishment and law relating to electronic commerce are not complete in China.So credit has become a critical obstacle for the development of online shopping,while customer credit is the most important component.In this paper,we construct a support vector machines(SVMs)ensemble method based on fuzzy integral to evaluate personal credit under the environment of electronic commerce.This method aggregates the outputs of separate component SVMs with importance of each component SVM.Empirical results show that SVM is effective and more advantageous than other methods.It is proved that the proposed method is stable,highly accurate,strong robust and feasible. It is useful for providing a sound credit assessment system.

关 键 词：电子商务 信用风险 支持向量机集成 

分 类 号：F713.36[经济管理—产业经济] F203F224