一种商业银行客户分割的多维方法——基于客户期望收益和态度的分割模型  

A Multi-dimention Customer Segmentation Model for Commercial Banks Based on Customer Anticipatory Earnings Attitude

作　　者：杜宽旗[1] 蒙肖莲[1] 蔡淑琴[2] 杨毓[2] 

机构地区：[1]南京理工大学经管学院,江苏南京210094 [2]华中科技大学管理学院,湖北武汉430074

出　　处：《商业研究》2006年第13期1-6,共6页Commercial Research

基　　金：国家自然科学基金资助项目;项目名称:企业客户关系管理中服务机理与支持平台的研究;项目编号:70271030;国家教育部社科基金规划基金项目;项目名称:高频金融时间序列预测数据挖掘方法研究;项目编号:474357

摘　　要：客户分割与资源分配是企业一直在努力解决的问题,但目前,空前巨大的客户数据量使得准确进行市场细分和寻找目标市场变得复杂和难以有效实施。通过数据挖掘技术从大型数据库中抽取隐藏的预测信息,利用层次聚类分析建立了一个根据客户的多个态度维度进行客户分割的多维方法。结果表明,以这一方式产生的聚类在同质性较好并且通过参考人口学特征的差别能够获得客户细分市场的轮廓。此外,识别了四个有特色的、表明对信息服务和技术有特殊偏好的客户群。Retailers have long recognized the importance of tailoring their marketing mixes to suit the specific needs and preferences of different customer groups.However, the access to unprecedented amounts of individual - level customer data may make it increasingly difficult to implement such targeted promotion. To meet this challenge, the paper examines the use of data mining as an alternative means of drawing, data pattem in large databases.In particular, with an agglomerative hierarchical merging method, it builds the model of customer segmentation based on the expected benefits of bank service and attitudes. The results indicate that the clusters generated in this way are more advantageous in their homogeneity and profile to customer segments gained by referring to demographic differences. Additionally, four characteristic groups of customers are identified showing special preferences for and against information services and technology.

关 键 词：客户分割模型 客户态度 层次聚类分析法 

分 类 号：F830.33[经济管理—金融学]