Evaluation of customer behavior with temporal centrality metrics for churn prediction of prepaid contracts

Abstract

The telecommunication industry is a saturated market where a proper implementation of a retention campaign is critical to be competitive, since retaining a customer is cheaper than attracting a new one. Hence, it is crucial to detect customer behavioral patterns and define accurate approaches to predict potential churners. Multiple researchers have used binary classification methods to predict churn of customers. Some of them verify that customers’ social relationships influence the decision of changing the operator.
We propose a novel method to extract the dynamic relevance of each customer using social network analysis techniques with a binary classification method called similarity forests. The dynamic importance of each customer is determined by applying various centrality metrics over temporal graphs, to represent the relationships between customers and to extract behavioral patterns of churners and non-churners. These relationships are established in a temporal graph using the call detail records (CDR) of telco’s customers. In this paper, we compare the performance of different centrality metrics applied over two types of temporal graphs: Time-Order Graph and Aggregated Static Graph.

More information

Identifiers

ORCID for Bart Baesens: orcid.org/0000-0002-5831-5668

Catalogue record

Export record

Altmetrics