Applying data mining to telecom churn management

By Shin-Yuan Hung, David Chi-Chung Yen, Hsiu-Yu Wang. Expert systems with applications, 2006

560 citations recorded by the source corpus.

Abstract Taiwan deregulated its wireless telecommunication services in 1997. Fierce competition followed, and churn management becomes a major focus of mobile operators to retain subscribers via satisfying their needs under resource constraints. One of the challenges is churner prediction. Through empirical evaluation, this study compares various data mining techniques that can assign a ‘propensity-to-churn’ score periodically to each subscriber of a mobile operator. The results indicate that both decision tree and neural network techniques can deliver accurate churn prediction models by using customer demographics, billing information, contract/service status, call detail records, and service change log.

Subfields: Information Systems, Marketing, Organizational Behavior and Human Resource Management

View Paper: https://www.semanticscholar.org/paper/9e39a8fa0c10314199d4f99aeaafdb124ea435de

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Marketing

In Organizational Behavior and Human Resource Management

Citations in the corpus

Application of data mining techniques in customer relationship management: A literature review and classification (2009, methodology): “…and neural network Kim (2006) Logistic regression, neural network and random forest Buckinx and Poel (2005) Neural network and decision tree Hung et al. (2006) Self-organizing map and Markov chain Kim et al. (2005) Logistic regression, neural network and decision tree Koh and Chan (2002),…”
Customer churn prediction in telecommunications (2012, background): “In addition, most of the literature (Hadden et al., 2006; Hung et al., 2006, 2010; John et al., 2007; Wei & Chiu, 2002) shows the features that are the aggregated call-details are important for the customer churn prediction.”
Customer churn prediction by hybrid neural networks (2009, methodology): “At first, we use the original dataset to train a MLP neural network as the baseline ANN model for comparisons, which is similar to related work, such as Buckinx and Van den Poel (2005) and Hung et al. (2006).”
Churn in Social Networks (2010, background): “Churn has been analysed in a wide range of industries: most widely in the telcom sector [44, 50, 41, 66, 17, 32, 13, 65, 30], but also in the field of retail business [12], banking [69], Internet service providers [31], service industries [53], P2P networks [28] and online games [34].”