2010 · 172 citations · 10 references
Churn prediction is critical for telecom operators because acquisition costs far exceed retention costs, and recent studies show that incorporating social proximity of recent churners can improve predictive accuracy beyond individual‑customer models. This study introduces Group‑First Churn Prediction, a framework that foregoes the need to know who has recently churned. The method identifies tightly connected subscriber groups using second‑order social metrics from information theory, detects group leaders through intra‑group interactions, and applies a statistical model based on group‑level KPIs to forecast churn for both groups and members. Experiments on a 16‑million‑subscriber dataset demonstrate that the approach outperforms conventional models and statistically captures social effects. Published in the 2010 SIAM International Conference on Data Mining (SDM), pages 732–741, DOI https://doi.org/10.1137/1.9781611972801.64, by Yossi Richter, Elad Yom‑Tov, and Noam Slonim.
Previous chapter Next chapter Full AccessProceedings Proceedings of the 2010 SIAM International Conference on Data Mining (SDM)Predicting customer churn in mobile networks through analysis of social groupsYossi Richter, Elad Yom-Tov, and Noam SlonimYossi Richter, Elad Yom-Tov, and Noam Slonimpp.732 - 741Chapter DOI:https://doi.org/10.1137/1.9781611972801.64PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract Churn prediction aims to identify subscribers who are about to transfer their business to a competitor. Since the cost associated with customer acquisition is much greater than the cost of customer retention, churn prediction has emerged as a crucial Business Intelligence (BI) application for modern telecommunication operators. The dominant approach to churn prediction is to model individual customers and derive their likelihood of churn using a predictive model. Recent work has shown that analyzing customers' interactions by assessing the social vicinity of recent churners can improve the accuracy of churn prediction. We propose a novel framework, termed Group-First Churn Prediction, which eliminates the a priori requirement of knowing who recently churned. Specifically, our approach exploits the structure of customer interactions to predict which groups of subscribers are most prone to churn, before even a single member in the group has churned. Our method works by identifying closely-knit groups of subscribers using second order social metrics derived from information theoretic principles. The interactions within each group are then analyzed to identify social leaders. Based on Key Performance Indicators that are derived from these groups, a novel statistical model is used to predict the churn of the groups and their members. Our experimental results, which are based on data from a telecommunication operator with approximately 16 million subscribers, demonstrate the unique advantages of the proposed method. We further provide empirical evidence that our method captures social phenomena in a highly significant manner. Previous chapter Next chapter RelatedDetails Published:2010ISBN:978-0-89871-703-7eISBN:978-1-61197-280-1 https://doi.org/10.1137/1.9781611972801Book Series Name:ProceedingsBook Code:PR136Book Pages:1-953
10
Social ties and their relevance to churn in mobile telecom networks
Koustuv Dasgupta, Rahul Singh, V. Balaji et al. · 2008 · 325 citations · Full text
Noam Slonim, Gurinder S. Atwal, Gašper Tkačik et al. · Proceedings of the National Academy of Sciences · 2005 · 222 citations · Full text
On the structural properties of massive telecom call graphs
Amit A. Nanavati, Siva Gurumurthy, Gautam Das et al. · 2006 · 153 citations · Full text