改进k-means算法在电信CRM客户分类中的应用  

Improved K-Means Algorithm and Its CRM in Telecom Customer Segmentation Application

作　　者：左国才[1] 周荣华[1] 黎自强[1] 

机构地区：[1]湖南软件职业学院软件工程系,湘潭411100

出　　处：《计算机系统应用》2012年第11期153-155,186,共4页Computer Systems & Applications

基　　金：湖南省教育厅科学研究项目(11C0724;11C0723)

摘　　要：电信市场的竞争在于客户的竞争,为了在激烈的竞争中保持优势,必须将客户进行细分,针对不同的客户,研究出相应的营销策略.K-means算法能对大型数据集进行高效分类,但对"噪声"敏感,聚类结果不准确,本文对该算法进行改进,使其能够实现更加准确和全面的客户细分.The telecommunication market competition is the competition for customers, in the fierce competition to maintain advantage, must be customer segmentation, for different customers, work out the corresponding marketing strategy. K-means algorithm for large data sets for efficient classification, but the ＂ noise＂ sensitive, clustering result is not accurate, the algorithm is improved, which can achieve a more accurate and comprehensive customer segmentation.

关 键 词：电信CRM 客户细分 数据挖掘 K-means聚类分析算法 

分 类 号：F274[经济管理—企业管理] F270.7[经济管理—国民经济] F626