A comparative study of social network classifiers for predicting churn in the telecommunication industry

Relational learning in networked data has been shown to be effective in a number of studies. Relational learners, composed of relational classifiers and collective inference methods, enable the inference of nodes in a network given the existence and strength of links to other nodes. These methods have been adapted to predict customer churn in telecommunication companies showing that incorporating them may give more accurate predictions. In this research, the performance of a variety of relational learners is compared by applying them to a number of CDR datasets originating from the telecommunication industry, with the goal to rank them as a whole and investigate the effects of relational classifiers and collective inference methods separately. Our results show that collective inference methods do not improve the performance of relational classifiers and the best performing relational classifier is the network-only link-based classifier, which builds a logistic model using link-based measures for the nodes in the network.

[1]  Bart Baesens,et al.  New insights into churn prediction in the telecommunication sector: A profit driven data mining approach , 2012, Eur. J. Oper. Res..

[2]  Bart Baesens,et al.  Analytics in a Big Data World: The Essential Guide to Data Science and its Applications , 2014 .

[3]  Amy Nicole Langville,et al.  Google's PageRank and beyond - the science of search engine rankings , 2006 .

[4]  Bart Baesens,et al.  Social network analysis for customer churn prediction , 2014, Appl. Soft Comput..

[5]  Foster J. Provost,et al.  Classification in Networked Data: a Toolkit and a Univariate Case Study , 2007, J. Mach. Learn. Res..

[6]  Frank W. Takes,et al.  Combining Customer Attribute and Social Network Mining for Prepaid Mobile Churn Prediction , 2013 .

[7]  Eric W. T. Ngai,et al.  Customer churn prediction using improved balanced random forests , 2009, Expert Syst. Appl..

[8]  Carlos Sarraute,et al.  A study of age and gender seen through mobile phone usage patterns in Mexico , 2014, 2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014).

[9]  David J. Hand,et al.  Measuring classifier performance: a coherent alternative to the area under the ROC curve , 2009, Machine Learning.

[10]  Jari Saramäki,et al.  Temporal motifs in time-dependent networks , 2011, ArXiv.

[11]  Kjersti Aas,et al.  Modelling and predicting customer churn from an insurance company , 2014 .

[12]  P. Jones,et al.  Inferring missing links in partially observed social networks , 2009, J. Oper. Res. Soc..

[13]  R. E. Lee,et al.  Distribution-free multiple comparisons between successive treatments , 1995 .

[14]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[15]  Sougata Mukherjea,et al.  Social ties and their relevance to churn in mobile telecom networks , 2008, EDBT '08.

[16]  Monique Snoeck,et al.  APATE: A novel approach for automated credit card transaction fraud detection using network-based extensions , 2015, Decis. Support Syst..

[17]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

[18]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[19]  Piotr Indyk,et al.  Enhanced hypertext categorization using hyperlinks , 1998, SIGMOD '98.

[20]  Bart Baesens,et al.  Modeling churn using customer lifetime value , 2009, Eur. J. Oper. Res..

[21]  Bart Baesens,et al.  Mining Telecommunication Networks to Enhance Customer Lifetime Predictions , 2014, ICAISC.

[22]  Natwar Modani,et al.  CDR Analysis Based Telco Churn Prediction and Customer Behavior Insights: A Case Study , 2013, WISE.

[23]  Chi-Hyuck Jun,et al.  Improved churn prediction in telecommunication industry by analyzing a large network , 2014, Expert Syst. Appl..

[24]  Gábor Benedek,et al.  The Importance of Social Embeddedness: Churn Models at Mobile Providers , 2014, Decis. Sci..

[25]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Bart Baesens,et al.  A Novel Profit Maximizing Metric for Measuring Classification Performance of Customer Churn Prediction Models , 2013, IEEE Transactions on Knowledge and Data Engineering.

[27]  Mohammad Mehdi Sepehri,et al.  Applying Data Mining to Customer Churn Prediction in an Internet Service Provider , 2010 .

[28]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[29]  Jens Perch Nielsen,et al.  Time-varying effects in the analysis of customer loyalty: A case study in insurance , 2012, Expert Syst. Appl..

[30]  Bart Baesens,et al.  Building comprehensible customer churn prediction models with advanced rule induction techniques , 2011, Expert Syst. Appl..

[31]  J. J. Rocchio,et al.  Relevance feedback in information retrieval , 1971 .

[32]  Cosma Rohilla Shalizi,et al.  Homophily and Contagion Are Generically Confounded in Observational Social Network Studies , 2010, Sociological methods & research.

[33]  Mark Newman,et al.  Networks: An Introduction , 2010 .

[34]  Kuan-Yu Chen,et al.  Customer Churn Prediction in Virtual Worlds , 2015, 2015 IIAI 4th International Congress on Advanced Applied Informatics.

[35]  Lise Getoor,et al.  Link-Based Classification , 2003, Encyclopedia of Machine Learning and Data Mining.

[36]  Monique Snoeck,et al.  GOTCHA! Network-Based Fraud Detection for Social Security Fraud , 2017, Manag. Sci..

[37]  Alex Berson,et al.  Building Data Mining Applications for CRM , 1999 .

[38]  Ji Zhu,et al.  Predicting customer churn through interpersonal influence , 2012, Knowl. Based Syst..

[39]  Dirk Van den Poel,et al.  Investigating the role of product features in preventing customer churn, by using survival analysis and choice modeling: The case of financial services , 2004, Expert Syst. Appl..

[40]  Bart Baesens,et al.  Combining local and social network classifiers to improve churn prediction , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[41]  David C. Yen,et al.  Applying data mining to telecom churn management , 2006, Expert Syst. Appl..

[42]  Jennifer Neville,et al.  Why collective inference improves relational classification , 2004, KDD.