基于KFAV的中国铁路货运客户细分方法研究

中国铁路货物运输由于诸多因素的影响,在客户和货源数量上受到了冲击,需要在客户关系管理及营销等方面不断完善,其中客户细分是精确营销的重要手段.本文提出了基于RFM模型的,新的客户分类KFAV模型,并对货运客户价值进行了计算.之后引入了局部密度值ρ和斥类值δ,对传统K均值(K-means)聚类方法在初始聚类中心选取方面进行了优化.通过搭建hadoop集群环境,采用spark计算框架,对选取的大量货票数据进行仿真.仿真结果显示,基于KFAV模型的铁路货运客户细分方法更加具有针对性,并且改进的K均值聚类方法提升了算法的效率,同时基于大数据分析的spark+hadoop平台极大地降低了客户细分的运行时间.

Railway Freight Customer Segmentation Based on KFAV Model

Because of various aspects influence, Chinese railway freight transportation is hit by the number of customers and sources of goods. One way to solve this problem is to improve the CRM (Customer Relationship Management) and market management. This paper proposes a new freight customer segmentation model, KFAV, which is derived from RFM model, and calculates the freight customers valued. Then a new improved K-means algorithm is proposed, which is used to cluster KFAV. The algorithm can optimize the initial center points through introducing two parameter, ρand δ, to compute the density of the members. Finally, this paper makes the simulation based on hadoop using spark. The simulation proves the freight customer segmentation based on KFAV is efficient, and the improved K- means algorithm is high efficiency.