Customer Relationship Management System for Retail Stores Using Unsupervised Clustering Algorithms with RFM Modeling for Customer Segmentation

• Published in: 2024 IEEE 14th Symposium on Computer Applications & Industrial Electronics (ISCAIE) pp. 1 - 6
• Main Authors: Ling, Sun Shuai, Too, Chian Wen, Wong, Whee Yen, Hoo, Meei Hao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.05.2024
• Subjects: Customer relationship management; Customer Segmentation; DBSCAN clustering; Decision making; GMM clustering; Gold; Industrial electronics; K-means Clustering; Noise; Platinum; RFM modeling; Silver; Unsupervised Clustering Algorithms
• ISSN: 2836-4317
• DOI: 10.1109/ISCAIE61308.2024.10576353

In the current scenario of a data-driven market, retailers and other business executives must comprehend and use the proper customer segmentation for the best of their business growth. Customer segmentation allows optimizing customer relationship management systems for personalized marketing strategies and improved customer engagement. In short, customer segmenting is largely dependent on the capability of data analysis tools to extract patterns and valuable information from vast databases. We performed unsupervised clustering algorithms including centroid-based clustering (K-means), hierarchical clustering, Density-Based Spatial Clustering of Applications with Noise (DBSCAN clustering), and distribution-based clustering (Gaussian Mixture Model) with recency, frequency, monetary (RFM) modeling to enhance customer segmentation within a customer relationship management (CRM) system. We found that the K-means clustering method and RFM modeling demonstrated optimal outcomes.