基于均值聚类的银行客户信用关系分析  

An Analysis on Credit Relationship of Bank Customer Based on K-MEANS Cluster

作　　者：许苗村[1] 蒋先刚[1] 

机构地区：[1]华东交通大学基础科学学院,江西南昌330013

出　　处：《华东交通大学学报》2008年第6期55-58,共4页Journal of East China Jiaotong University

摘　　要：针对银行业中客户贷款契约违约风险较高的问题,通过把经济学中的特征分析模型与数据挖掘中的K-MEANS聚类算法相结合,利用现有客户资料,对客户资信评级分类,从而实现对客户信息的高质量管理,降低银行对客户贷款的风险.实验结果表明,此算法对客户的资信评级具有良好的分类效果.Aiming at the high risk of customer loan contract violation in bank enterprise, combining a characteristic analysis model in economics with K-MEANS cluster algorithm in data mining, this paper carries on customer credit rating by using existing customer materials, thus realizing the high quality management of customer information, reducing the risk of bank loans. The experimental result indicates that this algorithm has good effect upon customer credit rating.

关 键 词：信用管理 客户资信评级 K-MEANS聚类 

分 类 号：TP315[自动化与计算机技术—计算机软件与理论]