Abstract
Rough set theory (RST) can be viewed as one of the classical set theory for handling with imprecision knowledge. The theory has discovered applications in numerous areas, for example, engineering, industries, environment and others. Churn in telecommunication sector, customer switching from one service provider to another. Predicting telecom customer churn is challenging due to the huge and inconsistent nature of the data. Churn prediction is crucial for telecommunication companies in order to build an efficient customer retention plan and apply successful marketing strategies. In this article, a methodology is proposed using RST to identify the efficient features for telecommunication customer churn prediction. Then the selected features are given to the ensemble-classification techniques such as Bagging, Boosting, Random Subspace. In this work the duke university-churn prediction data set is considered for performance evaluation and three sets of experiments are performed. Finally the performance of the proposed model is evaluated based on the following metrics such as true churn, false churn, specificity, precision and accuracy and it is identified that Proposed system designed with combining attribute selection with ensemble classification techniques works fine with classification accuracy of 95.13% compared to any single model.
Similar content being viewed by others
References
Chung BD, Park JH, Koh YJ, Lee S (2016) User satisfaction and retention of mobile telecommunications services in Korea. Int J Hum Comput Interact 32(7):532–543
Bose I, Chen X (2009) Hybrid models using unsupervised clustering for prediction of customer churn. J Organ Comput Electron Commer 19(2):133–151
Ali OG, Arturk U (2014) Dynamic churn prediction framework with more effective use of rare event data: the case of private banking. Expert Syst Appl 41(17):7889–7903
Cancho VG, Dey DK, Louzada F (2016) Unified multivariate survival model with a surviving fraction: an application to a Brazilian customer churn data. J Appl Stat 43(3):572–584
Gunther CC, Tvete IF, Aas K, Sandnes GI, Borgan Q (2014) Modelling and predicting customer churn from an insurance company. Scand Actuar J 1:58–71
Milosevic M, Zivic N, Andjelkovic I (2017) Early churn prediction with personalized targeting in mobile social games. Expert Syst Appl 83:326–332
Sankaranarayanan HB, Vishwanath BV, Rathod V (2016) An exploratory analysis for predicting passenger satisfaction at global hub airports using logistic model trees. In: 2016 Second international conference on research in computational intelligence and communication networks (ICRCICN). IEEE, pp 285–290
Bose I, Chen X (2009) Hybrid models using unsupervised clustering for prediction of customer churn. J Organ Comput Electron Commer 19(2):133–151
Gamulin N, Stular M, Tomazic S (2015) Impact of social network to churn in mobile network. Automatika 56(3):252–261
Vafeiadis T, Diamantaras KI, Sarigiannidis G, Chatzisavvas KC (2015) A comparison of machine learning techniques for customer churn prediction. Simul Model Pract Theory 55:1–9
Verbeke W, Martens D, Baesens B (2014) Social network analysis for customer churn prediction. Appl Soft Comput 14:431–446
Abbasimehr H, Setak M, Soroor J (2013) A framework for identification of high-value customers by including social network based variables for churn prediction using neuro-fuzzy techniques. Int J Prod Res 51(4):1279–1294
Farquad MAH, Ravi V, Raju SB (2014) Churn prediction using comprehensible support vector machine: an analytical CRM application. Appl Soft Comput 19:31–40
Huang B, Kechadi MT, Buckley B (2012) Customer churn prediction in telecommunications. Expert Syst Appl 39(1):1414–1425
Keramati A, Jafari-Marandi R, Aliannejadi M, Ahmadian I, Mozaffari M, Abbasi U (2014) Improved churn prediction in telecommunication industry using data mining techniques. Appl Soft Comput 24:994–1012
Khashei M, Hamadani AZ, Bijari M (2012) A novel hybrid classification model of artificial neural networks and multiple linear regression models. Expert Syst Appl 39(3):2606–2620
Abbasimehr H, Setak M, Tarokh MJ (2014) A comparative assessment of the performance of ensemble learning in customer churn prediction. Int Arab J Inf Technol 11(6):599–606
De Bock KW, Van den Poel D (2011) An empirical evaluation of rotation-based ensemble classifiers for customer churn prediction. Expert Syst Appl 38(10):12293–12301
De Bock KW, Van den Poel D (2012) Reconciling performance and interpretability in customer churn prediction using ensemble learning based on generalized additive models. Expert Syst Appl 39(8):6816–6826
Kim N, Jung KH, Kim YS, Lee J (2012) Uniformly subsampled ensemble (USE) for churn management: theory and implementation. Expert Syst Appl 39(15):11839–11845
Liu M, Qiao XQ, Xu WL (2011) Three categories customer churn prediction based on the adjusted real adaboost. Commun Stat Simul Comput 40(10):1548–1562
Lu N, Lin H, Lu J, Zhang G (2014) A customer churn prediction model in telecom industry using boosting. IEEE Trans Ind Inf 10(2):1659–1665
Xiao J, Xie L, He C, Jiang X (2012) Dynamic classifier ensemble model for customer classification with imbalanced class distribution. Expert Syst Appl 39(3):3668–3675
Droftina U, Stular M, Kosir A (2015) Predicting influential mobile-subscriber churners using low-level user features. Automatika 56(4):522–534
Idris A, Rizwan M, Khan A (2012) Churn prediction in telecom using random forest and PSO based data balancing in combination with various feature selection strategies. Comput Electr Eng 38(6):1808–1819
Idris A, Khan A, Lee YS (2013) Intelligent churn prediction in telecom: employing mRMR feature selection and RotBoost based ensemble classification. Appl intel 39(3):659–672
Maldonado S, Flores A, Verbraken T, Baesens B, Weber R (2015) Profit-based feature selection using support vector machinesGeneral framework and an application for customer retention. Appl Soft Comput 35:740–748
Sivasankar E, Vijaya J (2017) A study of feature selection techniques for predicting customer retention in Telecommunication sector. Int J Bus Inf Syst (In press)
Vijaya J, Sivasankar E (2017) An efficient system for customer churn prediction through particle swarm optimization based feature selection model with simulated annealing. Clust Comput 1–12
Xiao J, Xiao Y, Huang A, Liu D, Wang S (2015) Feature-selection-based dynamic transfer ensemble model for customer churn prediction. Knowl Inf Syst 43(1):29–51
Rajamohamed R, Manokaran J (2017) Improved credit card churn prediction based on rough clustering and supervised learning techniques. Clust Comput 1–13
Hudaib A, Dannoun R, Harfoushi O, Obiedat R, Faris H (2015) Hybrid data mining models for predicting customer churn. Int J Commun Netw Syst Sci 8(05):91
Huang Y, Kechadi T (2013) An effective hybrid learning system for telecommunication churn prediction. Expert Syst Appl 40(14):5635–5647
Duke University Case studies, Presentations and Video modules (2005): dataset available at http://www.fuqua.duke.edu/centers/ccrm/datasets/download.html/data
Pawlak Z (1982) Rough sets. Int J Comput Inf Sci 11(5):341–356
Amin A, Shehzad S, Khan C, Ali I, Anwar S (2015) Churn prediction in telecommunication industry using rough set approach. New trends in computational collective intelligence. Springer, Cham, pp 83–95
Inbarani HH, Bagyamathi M, Azar AT (2015) A novel hybrid feature selection method based on rough set and improved harmony search. Neural Comput Appl 26(8):1859–1880
Amin A, Anwar S, Adnan A, Nawaz M, Alawfi K, Hussain A, Huang K (2017) Customer churn prediction in the telecommunication sector using a rough set approach. Neurocomputing 237:242–254
Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
Kearns M, Valiant L (1994) Cryptographic limitations on learning Boolean formulae and finite automata. J ACM 41(1):67–95
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intel 20(8):832–844
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Vijaya, J., Sivasankar, E. Computing efficient features using rough set theory combined with ensemble classification techniques to improve the customer churn prediction in telecommunication sector. Computing 100, 839–860 (2018). https://doi.org/10.1007/s00607-018-0633-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00607-018-0633-6
Keywords
- Churn prediction
- Telecommunication
- Rough set theory
- Feature selection
- Ensemble classification
- Bagging
- Boosting
- Random subspace