基于改进协同过滤算法的电力营销渠道引流策略  

Power marketing channel diversion strategy based on improved collaborative filtering algorithm

作　　者：翟千惠 李明 蔡潇 程雅梦 俞阳 朱萌 ZHAI Qianhui;LI Ming;CAI Xiao;CHENG Yameng;YU Yang;ZHU Meng(Marketing Service Center,State Grid Jiangsu Electric Power Co.,Ltd.,Nanjing 210000,China;Xinghua Power Supply Branch Company,State Grid Jiangsu Electric Power Co.,Ltd.,Taizhou 225700,China;Taizhou Sanxin Power Supply Service Co.,Ltd.,Taizhou 225700,China)

机构地区：[1]国网江苏省电力有限公司营销服务中心,南京210000 [2]国网江苏省电力有限公司兴化市供电分公司,江苏泰州225700 [3]泰州三新供电服务有限公司,江苏泰州225700

出　　处：《电力需求侧管理》2023年第4期105-109,共5页Power Demand Side Management

基　　金：国网江苏省电力有限公司科技项目(J2020117)。

摘　　要：电力企业在数字化转型过程中,打造多渠道服务体系,充分利用“互联网+实体渠道”的方式,可以有效降低企业运营成本,为客户提供更加便捷、高效的服务。在上述背景下,提出了一种基于改进协同过滤算法的电力营销渠道引流策略,首先构造客户-属性数据矩阵,采用矩阵分解算法对原始客户属性矩阵中的缺失数据进行恢复,利用K-means算法对客户属性进行聚类。然后,利用客户混合类型属性相异性度量,通过基于用户的协同过滤推荐算法,寻找目标客户的K-最近邻矩阵,并制定出差异化的引流策略。最后以10万条缴费工单数据为例,分析了客户属性矩阵填充、不同度量方法与最近邻数目对引流准确率的影响,验证了所提算法的有效性和可行性。In the process of digital transformation,electric power enterprises can effectively reduce their operating costs and provide customers with more convenient and efficient services by building a multi-channel service system and making full use of the Internet+physical channels.Under the above background,a power:marketing channel diversion strategy based on improved collabora-tive filtering algorithm is proposed.Firstly,the customer attribute da-!matrix is constructed,and the matrix decomposition algorithm is used to recover the missing data in the original customer attribute matrix,and the K-means algorithm is used to cluster the customer at-tributes.Then,using the customer mixed type attribute dissimilarity measure,through the user based collaborative filtering recommenda-tion algorithm,the target customer s K-nearest neighbor matrix is found,and the diversion strategy of travel alienation is formulated.Finally,taking 100000 payment work order data as an example,the influence of customer attribute matrix flling,different measurement methods and the number of nearest neighbors on the drainage accura-cy are analyzed,and the efectiveness and feasibility of the proposed algorithm are found.

关 键 词：电力营销 数字化转型 改进协同过滤算法 Kmeans算法 K-最近邻矩阵 

分 类 号：TM73[电气工程—电力系统及自动化] F426.61[经济管理—产业经济]