基于数据挖掘的供电企业客户细分方法及模型研究  

Study on the customer segmentation model for power supply companies based on data mining

作　　者：张晓春[1] 倪红芳[1] 李娜[1] 

机构地区：[1]华北电力大学经济与管理学院,北京102206

出　　处：《科技与管理》2013年第6期104-109,共6页Science-Technology and Management

摘　　要：随着电网建设的不断完善升级,电力客户对于电力产品及其配套服务的品质要求不断提升,并且逐渐呈现高要求、差异化的发展趋势。面对客户需求的差异化和企业内部服务资源的有限性,供电企业有必要对客户进行科学合理的细分,实施差异化管理。下以供电企业的大数据为依托,运用数据挖掘技术,从客户的供电可靠性要求、客户价值和客户行为3个维度,建立细分指标体系,利用K-means聚类算法建立客户细分模型,并以南网某省为例进行实证分析,最终证明了所建立的细分模型是合理的。With the constant improvement and upgrade of the power grid construction, the requirements of the quali- ty for electrical products and supporting services continue to be enhanced for electricity customers, and gradually showing high demand and differentiated trends. Therefore, it is necessary to segment customers scientifically and rationally, and to implement diversity management. In this paper, a customer segmentation model has been estab- lished on the basses of the data mining technology. Firstly, a subdivision index system is created from the dimen- sions of power supply reliability requirements, customer value and customer behavior. Secondly, critical data is filtered from the power supply enterprise database. And finally, customers are segmented by using the K-means clustering algorithm. An empirical analysis is given in the last part which proved the reasonable of the segmentation model.

关 键 词：数据挖掘 K-MEANS聚类 客户价值 客户行为 客户细分 

分 类 号：F424.6[经济管理—产业经济]