Identifying prime customers based on mobileusage patterns

Abstract

Increasing competition has led telecommunications service providers to develop marketing strategies to retain their customers and attract new customers. Big data analytics offers some promising solutions that can aid telecommunications service providers in raising their revenues as well as designing better business strategies. In this work, we illustrate how usage behaviors of mobile phone users can be used to identify customers that generate more revenue. Additionally, telecommunications companies can also find a number of people in a customer’s network and can potentially use this information for their benefits. The companies can identify the users with a large network and encourage them to serve as ambassadors to promote their services within their networks in exchange for certain incentives. For experimentation in this paper, we used the strath/nodobo dataset (v.2011-03-23) [1] comprising of customers’ phone usage records. Unsupervised classification technique (clustering) is employed to find both high and low mobile usage customers based on the frequency of their calls, messages and their average call duration. Furthermore, users with a large number of outgoing calls and who are connected to many other users are also identified.