STM Journals Peer-reviewed research from Consortium e-Learning Network

E-Commerce for Future & Trends

Customer Segmentation for Enhancing Customer Centric Business

  1. M. Nivetha
  2. A. Meena Kowshalya

Abstract

Customer segmentation is grouping customers based on similarities so companies can approach each group for marketing effectively and appropriately. Customer segmentation is important for enhancing customer centric business for gaining retention among customers by campaigning them using better marketing strategies, causing more institutional benefit. This paper segments customers by analyzing their characteristics based on both demographic and behavioral attributes using K-Means clustering algorithm and Self-Organizing Maps (SOM). K-Means is a partitioning clustering algorithm which uses centroid based approach to provide promising clustering results with Davies Bouldin score of - 1.632 in 16 seconds. Self-Organizing Maps (SOM) provides easy visualization by reducing dimensionality. This paper combines both algorithmic features by re-clustering the cluster formed from SOM and K-Means algorithm. Experimentation in Rapid Miner and python shows improved results with more number of clusters. The Davies Bouldin score is estimated to be-1.702 and the execution time is 4 seconds.

Keywords

Support