ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Predictive Analysis of Customer Churn in Telecom Industry using Supervised Learning


Affiliations
1 Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology, India
     

   Subscribe/Renew Journal


Customer acquisition and retention is a key concern for several industries and is particularly acute in fiercely competitive and fast growth businesses. Retaining a loyal customer is far more important than acquiring a new one, thus making customer churn one of the critical concerns for big corporations. Finding factors triggering customer churn is vital to implement necessary remediation to pre-empt and cut back this churn. This research focuses on implementing machine learning (ML) algorithms to identify potential churn customers, categorise them based upon usage patterns, and visualize the analysis results. Results show that Extra Trees Classifier, XGBoosting Algorithm and Support Vector Machine have the best churn modelling performance, particularly for 80:20 dataset distribution with average AUC scores of 0.843, 0.787 and 0.735 respectively and low false negatives. The research demonstrates that ML algorithms can successfully predict potential customer churn and help in devising customer retention programmes.

Keywords

Customer or Client Retention, Customer Churn, Telecommunication Industry, Machine Learning.
Subscription Login to verify subscription
User
Notifications
Font Size

  • P. Kisioglu and I.Y. Topcu, “Applying Bayesian Belief Network Approach to Customer Churn Analysis: a Case Study on the Telecom Industry of Turkey”, Expert Systems with Applications, Vol. 38, No. 6, pp. 7151-7157, 2011.

  • B. Huang, M.T. Kechadi and B. Buckley, “Customer Churn Prediction in Telecommunications”, Expert Systems with Applications, Vol. 39, No. 1, pp. 1414-1425, 2012.

  • Bigml, “Churn in Telecom’s Dataset”, Available at: https://bigml.com/user/francisco/gallery/dataset/5163ad540c0b5e5b22000383

  • J.E.T. Akinsola, “Supervised Machine Learning Algorithms: Classification and Comparison”, International Journal of Computer Trends and Technology, Vol. 48, No. 3, pp. 128-138, 2017.

  • S. Sperandei, “Understanding Logistic Regression Analysis”, Biochemia Medica, Vol. 24, No. 1, pp. 1-12, 2014.

  • C.F. Tsai and Y.H. Lu, “Customer Churn Prediction by Hybrid Neural Networks”, Expert Systems Applications, Vol. 36, No. 10, pp. 12547-12553, 2009.

  • A. Ghorbani, F. Taghiyareh and C. Lucas, “The Application of the Locally Linear Model Tree on Customer Churn Prediction”, Proceedings of International Conference of Soft Computing and Pattern Recognition, pp. 472-477, 2009.

  • W. Verbeke, D. Martens, C. Mues and B. Baesens, “Building Comprehensible Customer Churn Prediction Models with Advanced Rule Induction Techniques”, Expert Systems with Applications, Vol. 38, 2011, pp. 2354-2364.

  • V. Yeshwanth, V.V. Raj, and M. Saravanam, “Evolutionary Churn Prediction in Mobile Networks using Hybrid Learning”, Proceedings of 24th Florida Conference on Artificial Intelligence Research Society, pp. 471-476, 2011.

  • S.C. Bagley, H. White and B.A. Golomb, “Logistic Regression in the Medical Literature: Standards for Use and Reporting, with Particular Attention to one Medical Domain”, Journal of Clinical Epidemiology, Vol. 54, No. 10, pp. 979-985, 2001.

  • Irina Rish, “An Empirical Study of the Naive Bayes Classifier”, Proceedings of 17th International Joint Conference on Artificial Intelligence, pp. 1-6, 2001.

  • A. Tharwat, “AdaBoost Classifier: An Overview”, Machine Learning Project, 2018.

  • R. Santhanam, N. Uzir, S. Raman Sunil and S. Banerjee, “Experimenting XGBoost Algorithm for Prediction and Classification of Different Datasets”, Proceedings of National Conference on Recent Innovations in Software Engineering and Computer Technologies, pp. 1-4, 2017.

  • Matteo Re and Giorgio Valentini, “Ensemble Methods: A Review”, Chapman and Hall Publisher, 2012.

  • Thanh-Nghi Do, “Parallel Multiclass Stochastic Gradient Descent Algorithms for Classifying Million Images with Very-High-Dimensional Signatures into Thousands Classes”, Vietnam Journal of Computer Science. Vol. 1, No. 2, pp. 107-115, 2014.

  • Pierre Geurts, Damien Ernst and Louis Wehenkel, “Extremely Randomized Trees”, Machine Learning, Vol. 63, No. 1, pp. 3-42, 2006.

  • Theodoros Evgeniou and Massimiliano Pontil, “Support Vector Machines: Theory and Applications”, Proceedings of International Conference on Machine Learning and its Applications, pp. 249-257, 2001.

  • Mohssen Mohammed, Muhammad Khan and Eihab Bashier, “Machine Learning: Algorithms and Applications”, CRC Press, 2016.

  • F. Fabris, D. Magalhaes, J. Pedro and A. Freitas, “A Review of Supervised Machine Learning Applied to Ageing Research”, Biogerontology, Vol. 18, No. 2, pp. 171-188, 2017.

  • Haim Shalit, “Calculating the Gini Index of Inequality for Individual Data”, Oxford Bulletin of Economics and Statistics, Vol. 47, No. 2, pp. 185-189, 2009.

  • Sarah Murphy, “Data Visualization and Rapid Analytics: Applying Tableau Desktop to Support Library Decision-Making”, Journal of Web Librarianship, Vol. 7, No. 2, pp. 465-476, 2013.

  • M. Sadiku, A. Shadare, S. Musa, C. Akujuobi and R. Perry, “Data Visualization”, International Journal of Engineering Research and Advanced Technology, Vol. 2, No. 12, pp. 11-16, 2016.


Abstract Views: 157

PDF Views: 0




  • Predictive Analysis of Customer Churn in Telecom Industry using Supervised Learning

Abstract Views: 157  |  PDF Views: 0

Authors

Shreyas Rajesh Labhsetwar
Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology, India

Abstract


Customer acquisition and retention is a key concern for several industries and is particularly acute in fiercely competitive and fast growth businesses. Retaining a loyal customer is far more important than acquiring a new one, thus making customer churn one of the critical concerns for big corporations. Finding factors triggering customer churn is vital to implement necessary remediation to pre-empt and cut back this churn. This research focuses on implementing machine learning (ML) algorithms to identify potential churn customers, categorise them based upon usage patterns, and visualize the analysis results. Results show that Extra Trees Classifier, XGBoosting Algorithm and Support Vector Machine have the best churn modelling performance, particularly for 80:20 dataset distribution with average AUC scores of 0.843, 0.787 and 0.735 respectively and low false negatives. The research demonstrates that ML algorithms can successfully predict potential customer churn and help in devising customer retention programmes.

Keywords


Customer or Client Retention, Customer Churn, Telecommunication Industry, Machine Learning.

References