Publication
Title
Social network analysis for customer churn prediction
Author
Abstract
This study examines the use of social network information for customer churn prediction. An alternativemodeling approach using relational learning algorithms is developed to incorporate social network effectswithin a customer churn prediction setting, in order to handle large scale networks, a time dependent classlabel, and a skewed class distribution. An innovative approach to incorporate non-Markovian networkeffects within relational classifiers and a novel parallel modeling setup to combine a relational and non-relational classification model are introduced. The results of two real life case studies on large scale telcodata sets are presented, containing both networked (call detail records) and non-networked (customerrelated) information about millions of subscribers. A significant impact of social network effects, includingnon-Markovian effects, on the performance of a customer churn prediction model is found, and theparallel model setup is shown to boost the profits generated by a retention campaign.
Language
English
Source (journal)
Applied soft computing. - Place of publication unknown
Publication
Place of publication unknown : 2014
ISSN
1568-4946
Volume/pages
14:C(2014), p. 431-446
ISI
000327529200011
Full text (Publisher's DOI)
Full text (publisher's version - intranet only)
UAntwerpen
Faculty/Department
Research group
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identification
Creation 26.11.2013
Last edited 11.06.2017
To cite this reference