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

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。

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

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 incveasingly 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 pattern 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.