Abstract: In CRM，customer segment is the base of other function.Completely thinking over the customer’s lifecycle value，it develops a novel customer segment method that combines group decision-making and data mining techniques.Firstly，it applies the analytic hierarchy process to determine the variables and the relative weights of every variable.Then，clustering techniques is applied to do customer segment according to the weighted variables.Finally，the data of an enterprise is used to validate the new method.The experimental results demonstrate that the method is effective for customer segment.

Key words: customer segment, data mining, customer’s lifecycle value, cluster

摘要： 客户细分是客户关系管理中基础的、重要的内容。全面考虑了客户生命周期价值，基于群体决策技术和数据挖掘技术提出了一种新的客户细分方法。在群体决策的基础上，确定影响客户细分的变量，利用层次分析法，确定各个变量的权重。利用数据挖掘的聚类技术，进行客户细分。用某橡胶企业的数据进行了验证，结果表明，该方法能够有效地支持企业的客户细分，为企业的决策提供依据。

关键词: 客户细分, 数据挖掘, 客户生命周期价值, 聚类