基于客户行为的4S店客户细分及其变化挖掘  

Customer Segmentation and Change Mining Based on Customer Behavior for 4S Shop

作　　者：郭崇慧[1] 赵作为 

机构地区：[1]大连理工大学系统工程研究所,辽宁大连116024

出　　处：《管理工程学报》2015年第4期18-26,共9页Journal of Industrial Engineering and Engineering Management

基　　金：国家自然科学基金资助项目(71171030;71031002);新世纪优秀人才支持计划项目(NCET-11-0050)

摘　　要：本文针对汽车售后维修服务业的特点,基于CRISP-DM模型提出了一种适合于4S店的客户细分方法与客户群变化挖掘方法。首先,根据汽车售后维修交易记录的特点,建立了基于客户行为的客户细分指标体系,接着运用自组织映射神经网络对客户进行聚类,通过对聚类结果进行分析与识别得到客户细分结果。其次,在客户细分结果的基础上,分别从客户群和客户个体两个角度对客户随时间变化情况进行了分析,提出了客户群在群数量及群属性上随时间变化的分析方法和客户个体的分群演变分析方法。最后,将本文方法在实际数据上进行了数值实验,实验结果表明了本文方法的可行性和有效性。With the rapid development of China＇s automobile industry, automobile enterprises are facing increasingly fierce competition. At the same time, with the dramatic growth in car ownership, automobile after-sales service market has become more and more beneficial. As a result, the competition among automobile enterprises has already changed from the car＇s sales to the after-sales service. As an important sector of automotive companies to maintain the customer relationship, the after-sales maintenance services department of 4S shop should accelerate the construction of the customer relationship management（CRM） system based on the information technology and take the customer as the center. For instance, a 4S shop needs to handle the vast customer group which consists of almost all the owners of its brand cars, and segment these customers. Data mining technologies have been applied more and more widely in business environment in recent years. After-sales maintenance services departments of 4S shop also hope to use the advanced data mining technologies to support enterprise customer segmentation and customer relationship management policy making. Many data mining technologies including K-means and Self-Organizing Map（SOM） methods can supply enterprises with better methods of segmenting their customers and developing marketing strategies tailored to specific segments and individuals. Experience, however, shows that business is ceaselessly changing and customers continue to evolve over time. Customer segments and related knowledge discovered from multiple data sources change over time as the customer base changes. However, much research has assumed that customer segments and their members are stable. To solve these problems, based on the characteristic of the automotive maintenance industry, this study discusses customer segmentation methods and customer cluster change mining methods based on the CRISP-DM model. After fully understanding the business needs and data attributes, a customer segmentation indicator

关 键 词：客户关系管理 客户细分 数据挖掘 

分 类 号：F27[经济管理—企业管理]