摘要
自中国铁路畅行常旅客计划实施以来,如何分析会员出行数据,搭建数据分析模型,对会员消费行为进行分类,应用多种数据分析算法挖掘会员对企业的价值,评价会员价值,进而针对性推出会员个性化营销方案,从而提升会员满意度和忠诚度是铁路客运营销的重要问题。以上述问题为研究目的,在结合铁路实际的基础上,通过改进传统客户价值模型(RFM模型),搭建多维度客户价值模型(RFMICT模型),运用数据挖掘技术中K-means聚类算法构建会员价值评价模型,以铁路会员数据为例,结合理论基础,对模型的分类结果进行分析,根据各客户类型消费特点提出针对性建议,为铁路客户关系管理和客运营销分析提供参考。
Since the implementation of the China Railway Frequent Traveler Plan, the core of railway passenger transport marketing has lain in the formulation of personalized marketing plans for members to improve their satisfaction and loyalty, which is based on analyzing members’ travel data, building data analysis models, classifying members’ consumption behaviors, mining values of members to the enterprise with various data analysis algorithms, and evaluating these membership values. With the above aspects as the research objective, this paper developed a multi-dimensional customer value model(RFMICT model) by improving the traditional customer value model(RFM model) and then utilized the K-means clustering algorithm in data mining technology to build the membership value evaluation model, taking into account the actual conditions of railway. With the railway membership data as an example, this paper analyzed the classification results of the model depending on a theoretical basis. In light of the consumption characteristics of different customer types, corresponding suggestions were proposed, which can provide a reference for railway customer management and passenger transport marketing analysis.
作者
黄巍
刘峰
HUANG Wei;LIU Feng(Beijing Railway Customer Service Center,China Railway Beijing Group Co.,Ltd.,Beijing 100860,China;Passenger Transport Department,China State Railway Group Co.,Ltd.,Beijing 100844,China)
出处
《铁道运输与经济》
北大核心
2021年第7期23-28,共6页
Railway Transport and Economy
基金
中国铁路总公司科技研究开发计划课题(2017X010-K)。
关键词
铁路
数据挖掘
聚类
常旅客
会员价值
客运营销
Railway
Data Mining
Clustering
Frequent Traveler
Membership Value
Passenger Transport Marketing
