In a high saturated market where a variety of MNOs (Mobile Network Operators) oer relatively homogeneous wireless technologies and services in the same area or region, customers have the freedom to choose the service based on any factor they deem important. In addition to this, mobile number portability contributes to a phenomenon called churning where customers migrate from one Mobile Network Operator (MNO) to another. Churning impacts not only the network design but also the pricing methods adopted by MNOs and, and hence their revenue. It is because of this that MNOs try to reduce churn through retention campaigns detecting potential churners before they leave the service. The mainstream approach to churn prediction considers each customer individually. Preliminary studies have shown that members in the social circle of a subscriber also inuence the subscriber to churn. Thus, systems that take social aspects into account poses an emerging theoretical challenge with potentially great practical implications. The state of the art has focused on proposing methods to identify churners based on data mining techniques, however these techniques doesn't always oer clear explanations for churn reasons. Instead, we use a technique called Agent-Based Modeling to model customers in the mobile telecommunication market and assess the eects of customers characteristics and behaviors on such market. We propose a model that includes some relevant demographic and psychographic characteristics and the utilizations of usage proles to describe customers individually. We propose to take into account social behavior. We modied an existing social network generator algorithm to take into account the user proles when creating a connection. We show through experimentation that using our approach, compared to not using social networks or homophily, yields better results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.