CUSTOMER CHURN PREDICTION AND RETENTION STRATEGY DEVELOPMENT USING EXPLAINABLE MACHINE LEARNING
Abstract
Customer churn is a severe problem for service companies since losses have a direct impact on profitability, revenue and long-term competitiveness. This research has created an interpretable machine learning model for customer churn prediction and designed a targeted retention strategy accordingly. The trained and evaluated four supervised learning models were Logistic Regression, Decision Tree, Random Forest and XGBoost and the following metrics were used for evaluation: Accuracy, Precision, Recall, Specificity, F1-Score, Balanced Accuracy, Matthews correlation coefficient, ROC-AUC and Precision–Recall AUC. XGBoost had the best overall predictive performance with ROC-AUC of 0.8545, PC-R AUC of 0.6724, PC-recall of 0.7941 and an F1 score of 0.6339 out of all the models evaluated. Explainability was added in the form of a SHapley Additive exPlanations (SHAP) analysis to highlight the key global and customer-level factors that affect churn. All the following were among the most influential: month-to-month contracts, short tenure, no dependents, higher monthly charges, fibre-optic internet service, electronic-check payment, no online security, and no online technical support. Customers were also separated into 4 groups: low risk, moderate risk, high risk, and critical risk according to their expected churn rates. Churn rate in the critical-risk segment was 71.74% while it was 2.17% in the low-risk segment. The results show the potential of explainable machine learning for enhancing customer churn prediction and managerial decisions by associating customer risk scores with interpretable churn drivers and value-based retention actions.
Downloads
References
2. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information fusion, 58, 82-115.
3. Barsotti, A., Gianini, G., Mio, C., Lin, J., Babbar, H., Singh, A., ... & Damiani, E. (2024). A decade of churn prediction techniques in the telco domain: a survey. SN Computer Science, 5(4), 404.
4. Belle, V., & Papantonis, I. (2021). Principles and practice of explainable machine learning. Frontiers in big Data, 4, 688969.
5. Borrego-Díaz, J., & Galán-Páez, J. (2022). Explainable Artificial Intelligence in Data Science: J. Borrego-Díaz, J. Galán-Páez. Minds and Machines, 32(3), 485-531.
6. Chang, V., Hall, K., Xu, Q. A., Amao, F. O., Ganatra, M. A., & Benson, V. (2024). Prediction of customer churn behavior in the telecommunication industry using machine learning models. Algorithms, 17(6), 231.
7. Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC genomics, 21(1), 6.
8. De Bock, K. W., & De Caigny, A. (2021). Spline-rule ensemble classifiers with structured sparsity regularization for interpretable customer churn modeling. Decision Support Systems, 150, 113523.
9. De Caigny, A., Coussement, K., Verbeke, W., Idbenjra, K., & Phan, M. (2021). Uplift modeling and its implications for B2B customer churn prediction: A segmentation-based modeling approach. Industrial Marketing Management, 99, 28-39.
10. Domingos, E., Ojeme, B., & Daramola, O. (2021). Experimental analysis of hyperparameters for deep learning-based churn prediction in the banking sector. Computation, 9(3), 34.
11. Emmert‐Streib, F., Yli‐Harja, O., & Dehmer, M. (2020). Explainable artificial intelligence and machine learning: A reality rooted perspective. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 10(6), e1368.
12. Geiler, L., Affeldt, S., & Nadif, M. (2022). An effective strategy for churn prediction and customer profiling. Data & Knowledge Engineering, 142, 102100.
13. Hedström, A., Weber, L., Krakowczyk, D., Bareeva, D., Motzkus, F., Samek, W., ... & Höhne, M. M. C. (2023). Quantus: An explainable ai toolkit for responsible evaluation of neural network explanations and beyond. Journal of Machine Learning Research, 24(34), 1-11.
14. Islam, M. R., Ahmed, M. U., Barua, S., & Begum, S. (2022). A systematic review of explainable artificial intelligence in terms of different application domains and tasks. Applied Sciences, 12(3), 1353.
15. Islam, S. R., Eberle, W., Ghafoor, S. K., & Ahmed, M. (2021). Explainable artificial intelligence approaches: A survey. arXiv preprint arXiv:2101.09429.
16. Jiang, P., Liu, Z., Abedin, M. Z., Wang, J., Yang, W., & Dong, Q. (2024). Profit-driven weighted classifier with interpretable ability for customer churn prediction. Omega, 125, 103034.
17. Khattak, A., Mehak, Z., Ahmad, H., Asghar, M. U., Asghar, M. Z., & Khan, A. (2023). Customer churn prediction using composite deep learning technique. Scientific Reports, 13(1), 17294.
18. Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020). Explainable ai: A review of machine learning interpretability methods. Entropy, 23(1), 18.
19. Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., ... & Lee, S. I. (2020). From local explanations to global understanding with explainable AI for trees. Nature machine intelligence, 2(1), 56-67.
20. Maldonado, S., López, J., & Vairetti, C. (2020). Profit-based churn prediction based on minimax probability machines. European Journal of Operational Research, 284(1), 273-284.
21. Marín Díaz, G., Galán, J. J., & Carrasco, R. A. (2022). XAI for churn prediction in B2B models: A use case in an enterprise software company. Mathematics, 10(20), 3896.
22. Mena, G., Coussement, K., De Bock, K. W., De Caigny, A., & Lessmann, S. (2024). Exploiting time-varying RFM measures for customer churn prediction with deep neural networks. Annals of Operations Research, 339(1), 765-787.
23. Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022). Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, 55(5), 3503-3568.
24. Nauta, M., Trienes, J., Pathak, S., Nguyen, E., Peters, M., Schmitt, Y., ... & Seifert, C. (2023). From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable ai. ACM Computing Surveys, 55(13s), 1-42.
25. Ouf, S., Mahmoud, K. T., & Abdel-Fattah, M. A. (2024). A proposed hybrid framework to improve the accuracy of customer churn prediction in telecom industry. Journal of Big Data, 11(1), 70.
26. TanKY. (2020). Telco customer churn: IBM dataset [Data set]. Kaggle. https://www.kaggle.com/datasets/yeanzc/telco-customer-churn-ibm-datase
This work is licensed under a Creative Commons Attribution 4.0 International License.
By submitting a manuscript to IJRDO – Journal of Business Management, the author(s) confirm that the work is original and does not infringe upon any existing copyrights or third-party rights.
Authors retain responsibility for the content of their work. In cases of proven ethical misconduct such as plagiarism or duplicate publication, the journal reserves the right to take appropriate action, which may include correction or retraction, in accordance with publication ethics.
