A Fuzzy Clustering Based Analysis of Migratory Customer Behavior

Customer clustering is used to identify behavioral patterns of customers so that businesses can align their marketing strategies with customers´ preferences and retain them. In this paper, we develop a method for extending the standard fuzzy c-means clustering algorithm for detection of temporal changes in customer behavior. The proposed method uses the idea of membership functions to identify how customers move between clusters over time. The study using real-life data leads to the discovery of new usage and revenue patterns of customers that occur due to the promotional activities of a mobile services provider, and identification of two groups of customers that exhibit migratory behavior overtime. The findings provide insights to mobile services providers about changes in customer behavior over time.