Detecting the migration of mobile service customers using fuzzy clustering

• We study migratory behavior of mobile services customers using fuzzy clustering.
• We propose an algorithm that studies how customers dynamically move between clusters.
• We discover new usage and revenue patterns for two migratory groups of customers.

Customer clustering is used to build customer profiles which make up the core of a customer centric information system. In this paper, we develop a method for extending the standard fuzzy c-means clustering algorithm using membership functions to detect how customers move between clusters over time. The study leads to the discovery of new usage and revenue patterns for customers, the identification of two groups of customers that exhibit migratory behavior over time, and the determination of specific usage and revenue attributes that impact customer migration. The findings provide insights to mobile services providers about how to detect temporal changes in customer behavior.