基于LRFAT模型和改进K-means的汽车忠诚客户细分方法

Translated title of the contribution: Automobile loyalty customer segmentation method based on LRFAT model and improved K-means clustering

Chunhua Ren, Linfu Sun, Qishi Wu

Research output: Contribution to journalArticlepeer-review

3 Scopus citations

Abstract

To realize precise marketing of automobile customers in the era of industrial Internet, it is necessary to cluster and effectively manage customer resources. Aiming at the low number of automobile loyal customers, high potential value and uneven data distribution, an improved customer segmentation LRFAT model based on RFM model was proposed. To improve the accuracy and stability of customer clustering, a method for selecting the initial cluster center of hierarchical K-nearest density peak was proposed with the inspiration of density peaks clustering, and the initial cluster center was selected to optimize K-means. On this basis, the automobile loyal customers were subdivided with improved K-means. Through the automobile sales application of a vehicle manufacturer, the effectiveness of the model and algorithm was verified. At the same time, the detailed analysis was made for different customer groups and the corresponding marketing suggestions were given.

Translated title of the contributionAutomobile loyalty customer segmentation method based on LRFAT model and improved K-means clustering
Original languageChinese (Traditional)
Pages (from-to)3267-3278
Number of pages12
JournalJisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS
Volume25
Issue number12
DOIs
StatePublished - Dec 1 2019

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Computer Science Applications
  • Industrial and Manufacturing Engineering
  • Electrical and Electronic Engineering

Keywords

  • Automobile loyal customer
  • Customer segmentation
  • Density peaks clustering
  • K-means clustering
  • LRFAT model

Fingerprint

Dive into the research topics of 'Automobile loyalty customer segmentation method based on LRFAT model and improved K-means clustering'. Together they form a unique fingerprint.

Cite this