Just-in-time customer churn prediction in the telecommunication sector

  • Adnan Amin
  • Feras Al-Obeidat
  • Babar Shah
  • May Al Tae
  • Changez Khan
  • Hamood Ur Rehman Durrani
  • Sajid Anwar


Due to the exponential growth in technologies and a greater number of competitors in the telecom sector, the companies are facing a rigorous problem of customer churns. The customer churn is a phenomenon that highlights the customer’s intention who may switch from a certain service or even the service provider company. Many customer churn prediction (CCP) techniques are developed by academics and practitioners to handle the customer churn in order to resolve the problems pertaining to customer retention. However, CCP is not widely studied in the scenario where the company is not having enough historical data due to either been a newly established company or due to the recent start of a new technology or even because of the loss of the historical data. The just-in-time (JIT) approach can be a more practical alternative to address this issue as compared to state-of-the-art CCP techniques. Unfortunately, similar to traditional churn prediction models, JIT also requires enough historical data. To address this gap in the traditional CCP models, this study uses the cross-company data, i.e., data from another company, in the context of JIT for addressing CCP problems in the telecom sector. We empirically evaluated the performance of the proposed model using publicly available datasets of two telecom companies. It is found from the empirical evaluation that in the JIT-CCP context: (i) it is possible to evaluate the performance of the predictive model using cross-company dataset for training purposes and (ii) it is evident that heterogeneous ensemble-based JIT-CCP model is more suitable approach to use as compared to individual classifier or homogeneous ensemble-based technique.


Cross-company Just-in-time Customer churn prediction Classification Homogeneous ensemble Heterogeneous ensemble 



The authors would like to thank Zayed University for their research fund supported under Research Incentive Fund (RIF) Activity Code: 17059.


  1. 1.
    Amin A, Faisal R, Muhammad R, Sajid A (2015) A prudent based approach for customer churn prediction. In: 11th International Conference, BDAS 2015, Ustroń, Poland, pp 320–332Google Scholar
  2. 2.
    Farquad MAH, Ravi V, Raju SB (2014) Churn prediction using comprehensible support vector machine: an analytical CRM application. Appl Soft Comput 19:31–40CrossRefGoogle Scholar
  3. 3.
    Chitra K, Subashini B (2011) Customer retention in banking sector using predictive data mining technique. In: ICIT 2011 5th International Conference on Information Technology, pp 1–4Google Scholar
  4. 4.
    Prasad Devi U, Madhavi S (2012) Prediction of churn behavior of bank customers. J Bus Intell 5(1):96–101Google Scholar
  5. 5.
    David Nunez-Gonzalez J, Grana M, Apolloni B (2014) Reputation features for trust prediction in social networks. Neurocomputing 166:1–7CrossRefGoogle Scholar
  6. 6.
    Verbeke W, Martens D, Baesens B (2014) Social network analysis for customer churn prediction. Appl Soft Comput 14:431–446CrossRefGoogle Scholar
  7. 7.
    Lin C-S, Tzeng G-H, Chin Y-C (2011) Combined rough set theory and flow network graph to predict customer churn in credit card accounts. Expert Syst Appl 38(1):8–15CrossRefGoogle Scholar
  8. 8.
    Soeini RA, Rodpysh KV (2012) Applying data mining to insurance customer churn management. Int Proc Comput Sci Inf Technol 30:82–92Google Scholar
  9. 9.
    Saron M, Othman ZA (2012) Academic talent model based on human resource data mart. Int J Res Comput Sci 2(5):29–35CrossRefGoogle Scholar
  10. 10.
    Suznjevic M, Stupar I, Matijasevic M (2011) MMORPG player behavior model based on player action categories. In: Proceedings of the 10th Annual Workshop on Network and Systems Support for Games. IEEE Press, pp 1–6Google Scholar
  11. 11.
    Chen K, Lei C (2006) Network game design: hints and implications of player interaction. In: Proceedings of the 5th ACM SIGCOMM Workshop on Network and Systems Support for Games, pp 1–9Google Scholar
  12. 12.
    Gök M, Jida J (2015) A case study for the churn prediction in Turksat Internet service subscription. In: IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp 1220–1224Google Scholar
  13. 13.
    Coussement K, Van den Poel D (2008) Churn prediction in subscription services: an application of support vector machines while comparing two parameter-selection techniques. Expert Syst Appl 34(1):313–327CrossRefGoogle Scholar
  14. 14.
    Kim K, Jun C-H, Lee J (2014) Improved churn prediction in telecommunication industry by analyzing a large network. Expert Syst Appl 41(15):6575–6584CrossRefGoogle Scholar
  15. 15.
    Kirui C, Hong L, Cheruiyot W, Kirui H (2013) Predicting customer churn in mobile telephony industry using probabilistic classifiers in data mining. IJCSI Int J Comput Sci Issues 10(2):165–172Google Scholar
  16. 16.
    Shaaban E, Helmy Y, Khedr A, Nasr M (2012) A proposed churn prediction model. Int J Eng Res Appl 2(4):693–697Google Scholar
  17. 17.
    Jaudet M, Hussain A, Iqbal N (2004) Neural networks for fault-prediction in a telecommunications network. In: Proceedings of the 8th IEEE International Multi-topic Conference (INMIC’2004), pp 24–26Google Scholar
  18. 18.
    Zakaryazad A, Duman E (2016) A profit-driven artificial neural network (ANN) with applications to fraud detection and direct marketing. Neurocomputing 175:121–131CrossRefGoogle Scholar
  19. 19.
    Kang C, Pei-ji S (2008) Customer churn prediction based on SVM-RFE. In: 2008 International Seminar on Business and Information Management, vol 1, pp 306–309Google Scholar
  20. 20.
    Burez J, Van den Poel D (2009) Handling class imbalance in customer churn prediction. Expert Syst Appl 36(3):4626–4636CrossRefGoogle Scholar
  21. 21.
    Mozer MC, Wolniewicz R, Grimes DB, Johnson E, Kaushansky H (2000) Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry. IEEE Trans Neural Netw 11(3):690–696CrossRefGoogle Scholar
  22. 22.
    Abbasimehr H (2011) A neuro-fuzzy classifier for customer churn prediction. Int J Comput Appl 19(8):35–41Google Scholar
  23. 23.
    Huang B, Kechadi MT, Buckley B (2012) Customer churn prediction in telecommunications. Expert Syst Appl 39(1):1414–1425CrossRefGoogle Scholar
  24. 24.
    Fukushima T, Kamei Y, Mcintosh S, Yamashita K, Ubayashi N (2014) An empirical study of just-in-time defect prediction using cross-project models. In: MSR-2015, Hyderabad, IndiaGoogle Scholar
  25. 25.
    Kamei Y, Fukushima T, McIntosh S, Yamashita K, Ubayashi N, Hassan AE (2016) Studying just-in-time defect prediction using cross-project models. Empirical Softw Eng 21(5):2072–2106CrossRefGoogle Scholar
  26. 26.
    García DL, Nebot À, Vellido A (2017) Intelligent data analysis approaches to churn as a business problem: a survey. Knowl Inf Syst 51(3):719–774CrossRefGoogle Scholar
  27. 27.
    Radisic M (2009) Just-in-time concept. Reterived May 20, pp 1–9Google Scholar
  28. 28.
    Fuchs M, Zanker M (2016) E-commerce and Web technologies, vol 123, p 2012Google Scholar
  29. 29.
    Kootanae AJ, Babu KN, Talari HF (2012) Just-in-time manufacturing system: from introduction to implement. Int J Econ Bus Financ 1(2):7–25Google Scholar
  30. 30.
    Witten IH, Frank E, Hall MA (2011) Data mining: practical machine learning tools and techniques. Morgan Kaufmann Publisher Inc., San Francisco, CA, p 664Google Scholar
  31. 31.
    Catolino G (2017) Just-in-time bug prediction in mobile applications? The domain matters! In: ACM MobileSoft 17. Argentina, Buenos Aires, pp 1–2Google Scholar
  32. 32.
    Kootanace A (2013) Just-in-time manufacturing system: from introduction to implement. Int J Econ Bus Financ 1(2):1–19Google Scholar
  33. 33.
    Burak T, Emilia M (2014) A comparison of cross- versus single-company effort prediction models for web projects. In: 40th Euromicro Conference on Software Engineering and Advanced Applications, pp 285–292Google Scholar
  34. 34.
    Briand K, El-Emam LC, Maxwell K, Surmann D, Wieczorek I (1999) An assessment and comparison of common cost estimation models. In: Proceedings of the 21st International Conference on Software Engineering, ICSE, pp 313–322Google Scholar
  35. 35.
    Briand IW, Langley LCT (2000) A replicated assessment of common software cost estimation techniques. In: International Proceedings of the 22nd Conference on Software Engineering. ICSE, pp 377–386Google Scholar
  36. 36.
    Jeffery R, Ruhe M, Wieczorek I (2000) A comparative study of two software development cost modeling techniques using multi-organizational and company-specific data. Inf Softw Technol 42:1009–1016CrossRefGoogle Scholar
  37. 37.
    Lefley M, Shepperd M (2003) Using genetic programming to improve software effort estimation based on general data sets. In: Proceedings of the GECCO 2003, LNCS 272a4. Springer, Berlin, pp 2477–2487Google Scholar
  38. 38.
    van Rijn JN, Holmes G, Pfahringer B, Vanschoren J (2015) Having a blast: meta-learning and heterogeneous ensembles for data streams. In: 2015 IEEE International Conference on Data Mining , pp 1–6Google Scholar
  39. 39.
    Wieczorek I, Ruhe M (2002) How valuable is company-specific data compared to multi-company data for software cost estimation? In: Proceedings of the 8th International Software Metrics Symposium. IEEE Computer Society Press, Ottawa, pp 237–246Google Scholar
  40. 40.
    Jeffery R, Ruhe M, Wieczorek I (2001) Using public domain metrics to estimate software development effort. In: Proceedings of the 7th International Software Metrics Symposium. IEEE Computer Society Press, London, pp 16–27Google Scholar
  41. 41.
    Maxwell K, Forselius P (2000) Benchmarking software development productivity. In: IEEE Software, pp 80–88Google Scholar
  42. 42.
    Mendes E, Mosley N, Counsell S (2003) Investigating early Web size measures for web cost estimation. In: Proceedings of the EASE’2003 Conference, Keele, pp 1–22Google Scholar
  43. 43.
    Idris A, Asifullah K (2014) Ensemble based efficient churn prediction model for telecom. In: 12th International Conference on Frontiers of Information Technology (FIT), pp 1–7Google Scholar
  44. 44.
    Guyon I, Gunn S, Nikravesh M, Zadeh LA (2006) Feature extraction, foundations and applications. Pattern Recognition, Springer, BerlinGoogle Scholar
  45. 45.
    Oyeniyi AO, Adeyemo AB (2015) Customer churn analysis in banking sector using data mining techniques. Afr J Comput ICT 8(3):165–174Google Scholar
  46. 46.
    Antreas D (2000) Customer satisfaction cues to support market segmentation and explain switching behavior. J Bus Res 47(3):191–207CrossRefGoogle Scholar
  47. 47.
    Ballings M, Poel DVD (2012) Customer event history for churn prediction. How long is long enough? Expert Syst Appl 39(8):13517–13522CrossRefGoogle Scholar
  48. 48.
    Buckinx W, Poel DVD (2005) Predicting online-purchasing behavior. Eur J Oper Res 166(2):557–575CrossRefzbMATHGoogle Scholar
  49. 49.
    Burez J, Van den Poel D (2007) CRM at a pay-TV company: using analytical models to reduce customer attrition by targeted marketing for subscription services. Expert Syst Appl 32(2):277–288CrossRefGoogle Scholar
  50. 50.
    Poku K, Zakari M, Sonali A (2013) Impact of service quality on customer loyalty in the hotel industry, an empirical study from Ghana. Int Rev Manag Bus Res 22:600–609Google Scholar
  51. 51.
    Kopcke H, Morik K (2004) Analyzing customer churn in insurance data, knowledge discovery in databases. In: PKDD 2004 Lecturer Notes of Computer Science, vol 202, pp 325–336Google Scholar
  52. 52.
    Mues C, Baesens B, Files CM, Vanthienen J (2004) Decision diagrams in machine learning: an empirical study on real-life credit-risk data. Expert Syst Appl 27(2):257–264CrossRefzbMATHGoogle Scholar
  53. 53.
    Thiyagarajan ABC, Anandha Kumar K (2016) A survey on diabetes mellitus prediction using machine learning techniques. Int J Appl Eng Res 11(3):973–4562Google Scholar
  54. 54.
    Hadden J, Tiwari A, Roy R, Ruta D (2007) Computer assisted customer churn management: state-of-the-art and future trends. Comput Oper Res 34(10):2902–2917CrossRefzbMATHGoogle Scholar
  55. 55.
    Mahajan V, Richa M, Renuka M (2015) Review of data mining techniques for churn prediction in telecom. J Inf Organ Sci 39(2):183–197Google Scholar
  56. 56.
    Kasiran Z, Ibrahim Z, Syahir M, Ribuan M (2014) Customer churn prediction using recurrent neural network with reinforcement learning algorithm in mobile phone users. Int J Intell Inf Process 5:1–11Google Scholar
  57. 57.
    Verbeke W, Sarraute C, Baesens B, Vanthienen J (2016) A comparative study of social network classifiers for predicting churn in the telecommunication industry. In: IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp 1151–1158Google Scholar
  58. 58.
    Amin Adnan et al (2016) Customer churn prediction in telecommunication sector using rough set approach. Neurocomputing 4:1–18Google Scholar
  59. 59.
    Vafeiadis T, Diamantaras KI, Sarigiannidis G, Chatzisavvas KC (2015) A comparison of machine learning techniques for customer churn prediction. Simul Model Pract Theory 55:1–9CrossRefGoogle Scholar
  60. 60.
    Rodan A, Fayyoumi A, Faris H, Alsakran J, Al-Kadi O (2015) Negative correlation learning for customer churn prediction: a comparison study. Sci World J 2015:1–7CrossRefGoogle Scholar
  61. 61.
    Khan I, Rehman GU, Usman T (2013) Intelligent churn prediction for telecommunication industry. Int J Innov Appl Stud 4(1):165–170Google Scholar
  62. 62.
    Garc’ıa DL, Nebot A, Alfredo V (2013) Visualizing pay-per-view television customers churn using cartograms and flow maps. In: ESANN 2013 Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp 24–26Google Scholar
  63. 63.
    Verbeke W, Dejaeger K, Martens D, Hur J, Baesens B (2012) New insights into churn prediction in the telecommunication sector: a profit driven data mining approach. Eur J Oper Res 218(1):211–229CrossRefGoogle Scholar
  64. 64.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297zbMATHGoogle Scholar
  65. 65.
    Cristianini N, Shawe-Taylor J (2000) An introduction to support vector machines and other kernel-based learning methods. Cam-bridge University Press, Cambridge, UKCrossRefzbMATHGoogle Scholar
  66. 66.
    Hornik K, Maxwell W, Halbert Stinchcombe (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366CrossRefGoogle Scholar
  67. 67.
    Wen S, Vahan B, Zeyar A, Wei LW (2013) Ensemble model for day-ahead electricity demand time series forecasting. In: Proceedings of the 4th International Conference Future Energy Systems, Berkeley, CA, USA, 2013, pp 51–62Google Scholar
  68. 68.
    Burez J, Poel D V d (2012) Data mining concepts and techniques. Pearson Education, LondonGoogle Scholar
  69. 69.
    Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13(1):21–27CrossRefzbMATHGoogle Scholar
  70. 70.
    Taneja S, Gupta C, Goyal K, Gureja D (2014) An enhanced k-nearest neighbor algorithm using information gain and clustering. In: 2014 Fourth International Conference on Advanced Computing and Communication Technologies, pp 325–329Google Scholar
  71. 71.
    Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques, ElsevierGoogle Scholar
  72. 72.
    Peng H (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238CrossRefGoogle Scholar
  73. 73.
    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(C):242–254. doi: 10.1016/j.neucom.2016.12.009
  74. 74.
    Amin A et al (2016) Comparing oversampling techniques to handle the class imbalance problem: a customer churn Prediction case study. IEEE Access 4:7940–7957. doi: 10.1109/ACCESS.2016.2619719 CrossRefGoogle Scholar
  75. 75.
    Amin A, Shah B, Anwar S, Al-Obeidat F, Khattak AM, Adnan A (2017) A prudent based approach for compromised user credentials detection. Clust Comput, pp 1–19. doi: 10.1007/s10586-017-0878-4
  76. 76.
    Amin A, Khan C, Ali I, Anwar S (2014) Customer churn prediction in telecommunication industry: with and without counter-example. In: 13th Mexican International Conference on Artificial Intelligence, MICAI 2014. Springer, Berlin, pp 206–218Google Scholar
  77. 77.
    Amin A, Anwar S, Adnan A, Khan MA, Iqbal Z (2015) Classification of cyber attacks based on rough set theory. In: 2015 1st International Conference on Anti-cybercrime, ICACC 2015Google Scholar
  78. 78.
    Basili V, Rombach H (1988) The TAME project: towards improvement-oriented software environment. IEEE Trans Softw Eng 14(6):758–773CrossRefGoogle Scholar
  79. 79.
  80. 80.
  81. 81.
    Smola A (1998) Learning with kernels, dissertation, Department of Computer Science, Technical University Berlin, GermanyGoogle Scholar
  82. 82.
    Kohavi R (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, pp 1137–1143Google Scholar
  83. 83.
    Wolpert DH (1992) Stacked generalization. Neural networks 5(2):241–259CrossRefGoogle Scholar
  84. 84.
    McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med 22(3):276–282MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  1. 1.Institute of Management SciencesPeshawarPakistan
  2. 2.College of Technological InnovationZayed UniversityAbu DhabiUAE

Personalised recommendations