一种改进的K_means算法在旅游客户细分中的应用  

An Improved K_means Algorithm and its Application to Tourists Classification

作　　者：汪永旗[1] 

机构地区：[1]浙江旅游职业学院旅管系,浙江杭州311231

出　　处：《宁波大学学报（理工版）》2012年第3期58-61,共4页Journal of Ningbo University：Natural Science and Engineering Edition

基　　金：浙江省旅游科学研究项目(2011ZC33);浙江旅游职业学院课题项目(2011XQZD02)

摘　　要：针对传统K_means算法存在的问题,提出一种基于密度的初始中心点选择方法,并利用几何三角形三边关系理论简化了迭代中的计算次数,以缩短大数据集聚类时间.针对旅游电子商务的特点,基于RFM模型设计了一种RFMVCI扩展模型.新算法的有效性和扩展模型的合理性在实验和旅游客户细分实践中获得了验证.An improved density-based K_means algorithm is presented for the existing problems of traditional K_means clustering algorithm, in which selection of initial center pointer is optimized. Also, the triangular trilateral relation theorem is introduced to reduce calculation complexity. An expanded RMF model （RFMVCI） is presented in applications of tourism electronic business, and the validity of new algorithm and rationality of extended model are validated in practice of tourism customer classification.

关 键 词：K_means 密度 RFM扩展模型 游客细分 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]