Abstract

Customer Churn Prediction problem is a long-standing challenge for Different communities, there are many groups in the scientific and commercial communities like telecom sector trying to improve Predictions. The primary motivation is the dire need of businesses to retain existing customers, coupled with the high cost associated with acquiring new one. The machine learning techniques have a significant impact onimproving and predicting customer data mining techniques to improve customer retention, but thesetechniques face a lot of challenges in terms of accuracy. This study aimed to enhance prediction and detection using a comparative study on the most popular supervised machinelearning methods , Support Vector Machine (SVM) andextreme Gradient Boosting (XGBoost) model to detectcustomer churn in IBM Watson dataset of telecom company. This paper provides XG boost classifier which less focused in the previousworks. XG boost classifier is applied on publicly available telecom dataset and experiential results are compared with SVM Classifier. XG boost classifier performs superior out of SVM.The evaluated metrics such as Precision, Recall, F1-score. It yielded an accuracy of the framework reached 84%.

References

• Coussement, K., Lessmann, S., & Verstraeten, G. (2017). A comparative analysis of data preparation algorithms for customer churn prediction: A case study in the telecommunication industry. Decision Support Systems, 95, 27–36. https://doi.org/10.1016/j.dss.2016.11.007.
• Óskarsdóttir, M., Bravo, C., Verbeke, W., Sarraute, C., Baesens, B., & Vanthienen, J. (2017). Social network analytics for churn prediction in telco: Model building, evaluation, and network architecture. Expert Systems with Applications, 85, 204–220. https://doi.org/10.1016/j.eswa.2017.05.028
• Huang, Y., Kechadi, T.: An effective hybrid learning system for telecommunication churn prediction. Expert Syst. Appl. 40, 5635– 5647 (2013)
• Applications of Data Mining Techniques for Churn Prediction and Cross-selling in the telecommunications Industry. (2019).
• Burez, Jonathan & Van den Poel, Dirk. (2007). CRM at a pay-tv company: Using analytical models to reduce customer attrition by targeted marketing for subscription services. Expert Syst. Appl.. 32. 277-288. 10.1016/j.eswa.2005.11.037.
• Saraswat, S. & Tiwari, A. (2018), ‘A New Approach for Customer Churn Prediction in Telecom Industry’, International Journal of Computer Applications, Vol. 181(11), pp. 40-46.
• Adwan, O., Faris, H., Jaradat, K., Harfoushi, O., & Ghatasheh, N. (2014). Predicting Customer Churn in Telecom Industry using MLP Neural Networks: Modeling and Analysis. Life Science Journal, 11(3), 1097–8135.https://doi.org/10.7537/marslsj110314.11
• H.S. Kim and C.H. Yoon, “Determinants of subscriber churn and customer loyalty in the Korean mobile telephony market,” Telecommunications Policy, vol. 28, no. 9, pp. 751–765, 2004.
• Kim, S., Chang, Y., Wong, S. F., & Park, M. C. (2020). Customer resistance to churn in a mature mobile telecommunications market. International Journal of Mobile Communications, 18(1), 41. https://doi.org/10.1504/ijmc.2020.104421
• Joseph3, H., & Sumaya, K. M. (2020.). Role of qualitative research in preventing customer churn: a case study of mobile network operators in Kenya.
• Carlo Vercellis, Business Intelligence: Data Mining and Optimization for Decision Making, John Wiley & Sons, Ltd. 2009 ISBN: 978-0-470-51138-1
• L. Deng and X. Li, “Machine learning paradigms for speech recognition: an overview,” IEEE Transactions on Audio Speech and Language Processing, vol. 21, no. 5, pp. 1060–1089, 2013.
• M. Q. Huang, J. Nini´c, and Q. B. Zhang, “Bim, machine learning and computer vision techniques in underground construction: current status and future perspectives,” Tunnelling and Underground Space Technology, vol. 108, Article ID 103677, 2021.
• P. Oza, P. Sharma, and S. Patel, “Machine learning applications for computer-aided medical diagnostics,” in Proceedings of the Second International Conference on Computing, Communications, and Cyber-Security Springer, New York, NY,USA, 2021.
• T. Bikmukhametov and J. J¨aschke, “Combining machine learning and process engineering physics towards enhanced accuracy and explainability of data-driven models,” Computers & Chemical Engineering, vol. 138, Article ID 106834, 2020.
• Awang, M. K., Makhtar, M., Nordin, M., & Rahman, A. (2013.). Improving Accuracy and Performance of Customer Churn Prediction Using Feature Reduction Algorithms.
• Shaaban, E., Helmy, Y., & Khedr, A. (2012). A Proposed Churn Prediction Model. Mona Nasr / International Journal of Engineering Research and Applications (IJERA), 2(4), 693–697. www.ijera.com
• Tsai, C.-F., & Lu, Y.-H. (2012). Data Mining Techniques in Customer Churn Prediction. Recent Patents on Computer Sciencee, 3(1), 28–32. https://doi.org/10.2174/2213275911003010028
• Lalwani, P., Sethi, P., Kumar, M., Jasroop, M., & Chadha, S. (2022). Customer churn prediction system : a machine learning approach. Computing, 104(2), 271–294. https://doi.org/10.1007/s00607-021-00908-y.
• Kumar, S., & D., C. (2016). A Survey on Customer Churn Prediction using Machine Learning Techniques. International Journal of Computer Applications, 154(10), 13–16. https://doi.org/10.5120/ijca2016912237
• Beschi Raja J, Chenthur Pandian S. An optimal ensemble classification for predicting Churn in telecommunication. J Eng Sci Technol Rev. 2020;13(2):44-49. doi:10.25103/jestr.132.07.
• Sarker IH. Machine Learning: Algorithms, Real-World Applications and Research Directions. SN Comput Sci. 2021;2(3):1-21. doi:10.1007/s42979-021-00592-x.
• Rustam, Z., Utami, D. A., Hidayat, R., Pandelaki, J., & Nugroho, W. A. (2019). Hybrid preprocessing method for support vector machine for classification of imbalanced cerebral infarction datasets. International Journal of Advanced Science, Engineering and Information Technology, 9(2), 685–691. https://doi.org/10.18517/ijaseit.9.2.8615
• J.Liu, E.Zio, “Integration of Feature Vector Selection and Support.
• Idris, A., Iftikhar, A., & Rehman, Z. ur. (2019). Intelligent churn prediction for telecom using GP-AdaBoost learning and PSO undersampling. Cluster Computing, 22. https://doi.org/10.1007/s10586-017-1154-3
• KALABALIK G, OKUR MC. a Comparison of the Performance of Ensemble Classification Methods in. Grad Sch Nat Appl Sci. Published online 2016.
• J. Hadden, A. Tiwari, R. Roy, and D. Ruta, "Computer assisted customer churn management: State-of-the-art and future trends," Computers & Operations Research. 34(10) (2007) 2902-2917.