Enhanced Churn Prediction Model Based on Comparative Analysis of Data Mining Classifier Algorithm

Enhanced Churn Prediction Model Based on Comparative Analysis of Data Mining Classifier Algorithm

Adeniyi Ben, Awodele, O., Ogbonna, A.C., Kuyoro, S.O., *Ebiesuwa Seun

Department of Computer Science, Babcock University, Nigeria

American Journal of Computer Engineering

Churn is characterized to be the movement of customers leaving the organization and disposing of the administrations offered by it because of the disappointment of the administrations as well as better offering from other network suppliers. To carry out a comparative analysis of the existing churn management models, we study the various characteristics of existing models based on techniques used methods of data classification and feature selection processes. Based on this comparison, this study can discover various types of knowledge, including association, classification, clustering, prediction, sequential patterns and decision tree. The knowledge acquired from this comparison will then be classified into general knowledge, primitive-level knowledge, and multilevel knowledge. To model the Customer prediction, a Markov Chain Model will be used. The Markov model allows for more flexibility than most other potential models, and can incorporate variables such as non-constant retention rate, which is not possible in the simpler models. The model allows looking at individual customer relationships as well as averages, and its probabilistic nature makes the uncertainty apprehensible. The purpose of this study was to ascertain the relevant drivers of customers` churn and retention in the growing telecommunication industry especially in Nigeria and developed an enhanced predictive model to address earlier limitation of accuracy and improved churn prediction. The enhanced churn prediction model performed better than the unenhanced model. Logistic regression had better performance metric than other algorithms: neural network, Support vector machine, decision tree and random forest. Although, all the other algorithm had a high AUC but in terms of generality and simplicity logistic regression resulted in the highest AUC value on performance statistics – Accuracy, Sensitivity, Specificity. More so, the result showed that internet service, types of contract entered, internet security were major factors that influence churn.

Keywords: Enhanced Churn Prediction Model, Data Mining Classifier Algorithm

Free Full-text PDF

How to cite this article:
Adeniyi Ben, Awodele, O., Ogbonna, A.C., Kuyoro, S.O., Ebiesuwa Seun. Enhanced Churn Prediction Model Based on Comparative Analysis of Data Mining Classifier Algorithm. American Journal of Computer Engineering, 2020; 3:7. (This article has been retracted from American Journal of Computer Engineering. Please do not use it for any purposes. )

1. Adebiyi, S.O., Oyatoye, E.O. & Amole, B.B. (2016). Relevant drivers for customers churn and retention decision in the Nigerian mobile telecommunication industry. JC, 8(3), 52-67
2. Adnan, A., Adnan, Z. Imran, A. Pir, S, Adeel, A., Basit, R., Ahmad, M. & Saif, M. (2017). Optimizing Coverage of Churn Prediction in Telecommunication Industry. International Journal of Advanced Computer Science and Applications, 8(5), 179 – 188
3. Ahmad, A.K., Jafar, A. & Aljoumaa, K. (2019). Customer churn prediction in telecom using machine learning in big data platform. JBD, 6(28), 1-24
4. Albadawi, S. et al (2017). Telecom churn prediction model using data mining techniques. BUJICT, 10(2), 8-14
5. Ali Dehghan, Theodore B. Trafalis (2012. Examining churn and loyalty using support vector machine. Scienceedu Press, (4), 153161
6. 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, 2(1), 242–254.
7. Amin, A., Khan, C., Imtiaz, A., & Anwar, S. (2014). Customer Churn Prediction in Telecommunication Industry: With and Without Counter-Example, 206-218
8. Anjum, A. et al (2017). Optimizing coverage of churn prediction in telecommunication Industry. 8(5): 179-188
9. Ascarza, E. (2017). In pursuit of enhanced customer retention management: review, Key issues and Future directions
10. Belal A.R.(2016). Corporate social responsibility reporting in developing countries: The case of Bangladesh. Routledge, Ltd
11. Bernard, H.R. (2002). Research methods in anthropology. Qualitative and quantitative approaches (3rd ed.). California: Altamira Press.
12. Bradbury, B.L. & Mather, P.C. (2009). The Integration of First-year, first-generation college students from ohio Appalachia. NASPA, 46 (92) 258-281
13. Bryan, E. & Simmons, L.A. (2009). Family Involvement: Impacts on Post-secondary educational success for first-generation Appalachian college students. JCSD, 50 (4), 391-405
14. Canale, A. & Lunardon, N. (2014). Churn prediction in telecommunication industry: A study based on Bagging Classifiers. Cellegio Carlo Alberto 350
15. Chuanqi, W., Ruiqi, L. Peng, W., Zonghai, C. (2017). Partition costsensitive CART based on customer value for Telecom customer Churn Prediction, Control Conference (CCC),
16. 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(2), 27–36.
17. Hassounna et al (2015). Customer churn in mobile markets: A comparison of Techniques. IBS, 8(6), 224-237
18. He, B., Shi, Y., Wan, Q. & Zhao, X. (2014). Prediction of customer attrition of commercial banks based on SVM model. Procedia Computer Science, 31(2), 423–430
19. Hejazinia, R. & Kazemi, M. (2014). Prioritizing factors influencing customer churn. IJCRB, 5(12), 227-236
20. Huang, Y. et al (2015). Telco churn prediction with big data, 2(3), 607-618
21. Idris, A., Iftikhar, A. & Rehman, Z. (2017). Intelligent churn prediction for telecom using GP-AdaBoost Learning and PSO Undersampling.
22. Induja, S. & Eswaramurthy, V.P. (2016). Customers churn prediction and attribute selection in telecom industry using kernelized extreme learning machine and bat algorithms. IJSR 5(12), 258-265
23. Jae Sik, Lee & Chun Lee, Jin. (2006). Customer churn Prediction by Hybrid Model.
24. Jamalian, E. & Foukerdi, R. (2018). A hybrid data mining method for customer churn prediction. ETASR 8(3), 2991-2997
25. Shandiz M. A. (2015) Application of machine learning and data mining methods for churn rate prediction of customers.
26. Sithole, B.T. & Njaya, T. (2018). Regional perspectives of the determinants of customer churn behaviour in various industries in Asia, Latin America and Sub-Saharan Africa. SJEBM 5(3), 211-217
27. Skymind (2019). A beginner’s guide to neural networks and deep learning. Retrieved from https://skymind.ai
28. Sufian, A., Khalid, L., Muhammad, M., & Kharbat, F. (2017). Telecom churn prediction model using data mining technique
29. Tsymbalov, E. (2016). Churn Prediction for Game Industry Based on Cohort Classification Ensemble. MPRA 82871
30. Umayaparvathi, V. & Iyakutti, K. (2016). A Survey on Customer Churn Prediction in Telecom Industry: Datasets, Methods and Metrics. IRJET 3(4), 1065-1070
31. Vafeiadis, T., Diamantaras, K. I., Sarigiannidis, G., & Chatzisavvas, K. C. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modelling Practice and Theory. 55(2), 1–9.