Prediction of Subscriber Churn Using Social Network Analysis

Abstract

In today's world, mobile phone penetration has reached a saturation point. As a result, subscriber churn has become an important issue for mobile operators as subscribers switch operators for a variety of reasons. Mobile operators typically employ churn prediction algorithms based on service usage metrics, network performance indicators, and traditional demographic information. A newly emerging technique is the use of social network analysis (SNA) to identify potential churners. Intuitively, a subscriber who is churning will have an impact on the churn propensity of his social circle. Call detail records are useful to understand the social connectivity of subscribers through call graphs but do not directly provide the strength of their relationship or have enough information to determine the diffusion of churn influence. In this paper, we present a way to address these challenges by developing a new churn prediction algorithm based on a social network analysis of the call graph. We provide a formulation that quantifies the strength of social ties between users based on multiple attributes and then apply an influence diffusion model over the call graph to determine the net accumulated influence from churners. We combine this influence and other social factors with more traditional metrics and apply machine‐learning methods to compute the propensity to churn for individual users. We evaluate the performance of our algorithm over a real data set and quantify the benefit of using SNA in churn prediction. © 2013 Alcatel‐Lucent.

Determination of Friendship Intensity between Online Social Network Users Based on their Interaction

“…The primary application is to use a model in order to improve the service of OSN [9]. Telecoms are trying to detect possible churners (users that are likely to change network) by analysing social network where a stronger link or tie means a greater influence between users [18][19][20]. Usually information for building that kind of social network is fetched from call detail records (CDR).…”

A social model based on customers’ profiles for analyzing the churning process in the mobile market of data plans

“…A churn prediction algorithm that quantifies the strength of social ties, which are defined by means of several parameters, is presented in [28]. Later on, over this scenario, the authors apply a diffusion model to assess the influence of churners.…”

“…In [26] is argued that churn is an event due to personal decisions and outlines, and of course, it is affected by external occurrences and, among them, by the impacts of the community where this individual belongs. In [28], the authors present an approach that takes into account intrinsic and extrinsic factors, using the idea of Collective Classification (CC). With this in mind, we decided it was important that the proposed model took into account social behavior.…”

Time series for early churn detection: Using similarity based classification for dynamic networks

“…In business-oriented contexts, where costs and benefits are a concern, it is furthermore valuable to detect the potential churners early enough for the campaigns to achieve optimal success and maximize their return (Verbraken et al, 2013). Research has shown that features that incorporate the influence of prior churners in a customer's social circle -their ego-net-are usually good predictors of churn when it is treated as a binary classification problem (Óskarsdóttir et al, 2017;Verbeke et al, 2014;Phadke et al, 2013). These features are extracted from call networks which are constructed based on call detail records (CDR) by linking together customers who have called or texted each other.…”