An enhanced ensemble classifier for telecom churn prediction using cost based uplift modelling

Telecom, being a dynamic and competitive industry which contains an inherently high potential for customer churn, necessitating of accurate churn prediction models. Regular classification approaches fail to effectively predict churn due to low correlation levels between conventional performance metrics and business goals. This work presents an ensemble stacking incorporated with uplifting-based strategies for telecom churn prediction model. Evaluations have been performed based on conventional performance and a cost heuristic, with a major focus upon the cost heuristic. This mode of operation exhibits a high correlation levels between performance indicators and business goals, thus enabling the algorithm suitable for most cost-sensitive applications. A heterogeneous ensemble is created by using multiple algorithms to provide first level predictions. Those predictions with discrepancies are processed at the secondary level using a heuristic based combiner to provide the final predictions. Combination heuristics are fine-tuned based on the cost to predict more accurately concentrating on business goals. Subsequently, Customer uplifting is performed on final predictions, thus making the proposed model 50% more cost efficient than the state-of-the-art ensemble models.

[1]  Dirk Van den Poel,et al.  Customer base analysis: partial defection of behaviourally loyal clients in a non-contractual FMCG retail setting , 2005, Eur. J. Oper. Res..

[2]  Phillip E. Pfeifer,et al.  Marketing Metrics: The Definitive Guide to Measuring Marketing Performance , 2010 .

[3]  Vadlamani Ravi,et al.  Predicting credit card customer churn in banks using data mining , 2008, Int. J. Data Anal. Tech. Strateg..

[4]  Chih-Ping Wei,et al.  Turning telecommunications call details to churn prediction: a data mining approach , 2002, Expert Syst. Appl..

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

[6]  Balaji Padmanabhan,et al.  From information to operations: Service quality and customer retention , 2011, TMIS.

[7]  A. E. Eiben,et al.  Genetic Modelling of Customer Retention , 1998, EuroGP.

[8]  Bart Baesens,et al.  Toward profit-driven churn modeling with predictive marketing analytics , 2012, CloudCom 2012.

[9]  Venusmar C. Quevedo,et al.  Predicting Customer Lifetime Value through Data Mining Technique in a Direct Selling Company , 2016, 2016 International Conference on Industrial Engineering, Management Science and Application (ICIMSA).

[10]  Kristof Coussement,et al.  Faculteit Economie En Bedrijfskunde Hoveniersberg 24 B-9000 Gent Churn Prediction in Subscription Services: an Application of Support Vector Machines While Comparing Two Parameter-selection Techniques Churn Prediction in Subscription Services: an Application of Support Vector Machines While Comparin , 2022 .

[11]  Björn E. Ottersten,et al.  A novel cost-sensitive framework for customer churn predictive modeling , 2015, Decis. Anal..

[12]  Ron Kohavi,et al.  The Case against Accuracy Estimation for Comparing Induction Algorithms , 1998, ICML.

[13]  A. Athanassopoulos.  Customer Satisfaction Cues To Support Market Segmentation and Explain Switching Behavior , 2000 .

[14]  Pratima Sharma,et al.  HONEYDOS: a hybrid approach using data mining and honeypot to counter denial of service attack and malicious packets , 2018 .

[15]  D. Maheswari,et al.  Churn prediction on huge telecom data using hybrid firefly based classification , 2017 .

[16]  Kaizhu Huang,et al.  Customer churn prediction in the telecommunication sector using a rough set approach , 2017, Neurocomputing.

[17]  Wagner A. Kamakura,et al.  Defection Detection: Measuring and Understanding the Predictive Accuracy of Customer Churn Models , 2006 .

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

[19]  Christophe Croux,et al.  Bagging and Boosting Classification Trees to Predict Churn , 2006 .

[20]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[21]  Charles Elkan,et al.  The Foundations of Cost-Sensitive Learning , 2001, IJCAI.

[22]  Susan M. Keaveney,et al.  Customer Switching Behavior in Service Industries: An Exploratory Study , 1995 .

[23]  Dirk Van den Poel,et al.  Predicting customer retention and profitability by using random forests and regression forests techniques , 2005, Expert Syst. Appl..

[24]  Hossam Faris,et al.  A Genetic Programming Based Framework for Churn Prediction in Telecommunication Industry , 2014, ICCCI.

[25]  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.

[26]  C. Bhattacharya.  When customers are members: Customer retention in paid membership contexts , 1998 .

[27]  Dirk Van den Poel,et al.  CRM at a pay-TV company: Using analytical models to reduce customer attrition by targeted marketing for subscription services , 2007, Expert Syst. Appl..

[28]  Bin Li,et al.  Automated Cellular Modeling and Prediction on a Large Scale , 2000, Artificial Intelligence Review.

[29]  Dirk Van den Poel,et al.  Customer attrition analysis for financial services using proportional hazard models , 2004, Eur. J. Oper. Res..

[30]  Chih-Fong Tsai,et al.  Customer churn prediction by hybrid neural networks , 2009, Expert Syst. Appl..

[31]  Konstantinos I. Diamantaras,et al.  A comparison of machine learning techniques for customer churn prediction , 2015, Simul. Model. Pract. Theory.

[32]  Eric Johnson,et al.  Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry , 2000, IEEE Trans. Neural Networks Learn. Syst..