CFP last date
20 May 2026
Call for Paper
June Edition
IJCA solicits high quality original research papers for the upcoming June edition of the journal. The last date of research paper submission is 20 May 2026

Submit your paper
Know more
The week's pick
Responsive image
REVENUE FORECASTING IN INTELLIGENT WATER MANAGEMENT SYSTEMS USING ARIMA TIME SERIES MODEL

Coraina Y. Torar Gloria Manggala Meilani J. Ngantung
Random Articles
Reseach Article

Predicting Voluntary Subscriber Churn through Engagement-Centric Machine Learning Models

by Wael Breich
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 187 - Number 99
Year of Publication: 2026
Authors: Wael Breich
10.5120/ijca78ca8817ceb3

Wael Breich . Predicting Voluntary Subscriber Churn through Engagement-Centric Machine Learning Models. International Journal of Computer Applications. 187, 99 ( Apr 2026), 12-18. DOI=10.5120/ijca78ca8817ceb3

@article{ 10.5120/ijca78ca8817ceb3,
author = { Wael Breich },
title = { Predicting Voluntary Subscriber Churn through Engagement-Centric Machine Learning Models },
journal = { International Journal of Computer Applications },
issue_date = { Apr 2026 },
volume = { 187 },
number = { 99 },
month = { Apr },
year = { 2026 },
issn = { 0975-8887 },
pages = { 12-18 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume187/number99/predicting-voluntary-subscriber-churn-through-engagement-centric-machine-learning-models/ },
doi = { 10.5120/ijca78ca8817ceb3 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2026-04-28T21:29:24+05:30
%A Wael Breich
%T Predicting Voluntary Subscriber Churn through Engagement-Centric Machine Learning Models
%J International Journal of Computer Applications
%@ 0975-8887
%V 187
%N 99
%P 12-18
%D 2026
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Customer churn is a critical challenge in subscription-based industries due to its direct impact on revenue stability, customer lifetime value, and long-term growth. With the growing availability of behavioral data, churn prediction has become a prominent application for assessing both predictive performance and model interpretability in data mining and analytics. However, much of the existing literature relies on heterogeneous feature sets that combine engagement metrics with demographic, contractual, and pricing variables, which can limit interpretability and obscure the independent role of engagement behavior. This study investigates whether engagement-centric behavioral metrics alone are sufficient to predict voluntary customer churn. Using a real-world customer-level dataset, normalized engagement features were constructed to capture usage frequency, consumption intensity, engagement breadth, and service reliability while accounting for differences in exposure duration through tenure normalization. Logistic regression, random forest, and gradient boosting (XGBoost) models are benchmarked to evaluate predictive performance and to assess the importance of nonlinear and interaction effects. To enhance interpretability, SHapley Additive exPlanations (SHAP) are applied to the gradient boosting model to quantify the marginal contribution of individual engagement features. Results show that engagement-only features provide strong predictive performance, with nonlinear ensemble models substantially outperforming linear baselines. The SHAP analysis reveals that low engagement frequency and reduced interaction breadth are the dominant drivers of churn risk, exhibiting pronounced nonlinear effects at low activity levels. Overall, the findings demonstrate that engagement behavior offers a robust and interpretable foundation for explainable churn prediction.

References
  1. E. Ascarza, “Retention futility: Targeting high-risk customers might be ineffective,” J. Marketing Res., vol. 55, no. 1, pp. 80–98, 2018.
  2. M. Bogaert and L. Delaere, “A systematic review of customer churn prediction using machine learning techniques,” Mathematics, vol. 11, no. 5, p. 1137, 2023.
  3. P. Wachwanakijkul, S. Junsiritrakhoon, N. Kantanantha, G. Narayanamurthy, and P. Jarumaneeroj, “Customer churn prediction: A comprehensive survey of machine learning approaches,” Big Data Cogn. Comput., vol. 9, no. 3, 2025.
  4. M. Imani, M. Joudaki, A. Beikmohammadi, and H. R. Arabnia, “A survey of customer churn analysis in data driven environments,” Big Data Cogn. Comput., vol. 7, no. 3, p. 105, 2025.
  5. S. Kaisar, M. Rashid, A. Chowdhury, S. S. Shafin, J. Kamruzzaman, and A. Diro, “Enhancing telemarketing success using ensemble-based learning,” Big Data Mining and Analytics, vol. 7, no. 1, pp. 1–14, 2024.
  6. A. De Caigny, K. Coussement, K. W. De Bock, and S. Lessmann, “Incorporating textual information in customer churn prediction models based on a convolutional neural network,” Decision Support Syst., vol. 129, p. 113189, 2020.
  7. T. Xu, Y. Ma, and K. Kangchul, “Customer churn prediction using ensemble learning and feature selection,” Appl. Sci., vol. 11, no. 11, p. 4742, 2021.
  8. S. M. Shrestha and A. Shakya, “Customer churn prediction using machine learning techniques,” Procedia Comput. Sci., vol. 198, pp. 86–93, 2022.
  9. A. K. Ahmad, A. Jafar, and K. Aljoumaa, “Customer churn prediction in telecom using machine learning in big data platform,” J. Big Data, vol. 6, no. 1, 2019.
  10. S. M. Mirabdolbaghi and B. Amiri, “Model optimization analysis of customer churn prediction using machine learning algorithms with focus on feature reduction,” Expert Syst., vol. 39, no. 6, 2022.
  11. V. Chang, K. Hall, Q. A. Xu, F. O. Amao, M. A. Ganatra, and V. Benson, “Explainable AI for customer churn prediction in digital services,” Information, vol. 17, no. 6, p. 231, 2024.
  12. E. Stripling, S. Vanden Broucke, K. Antonio, B. Baesens, and M. Snoeck, “Profit-driven decision trees for churn prediction,” Decision Support Syst., vol. 111, pp. 28–41, 2018.
  13. S. Höppner, E. Stripling, B. Baesens, S. Vanden Broucke, and T. Verdonck, “Profit-driven churn prediction with customer lifetime value,” Eur. J. Oper. Res., vol. 284, no. 3, pp. 920–934, 2020.
  14. S. Maldonado, J. López, and C. Vairetti, “Profit-based feature selection for churn prediction,” Eur. J. Oper. Res., vol. 283, no. 3, pp. 1086–1098, 2020.
  15. R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and D. Pedreschi, “A survey of methods for explaining black box models,” ACM Comput. Surv., vol. 51, no. 5, pp. 1–42, 2018.
  16. A. B. Arrieta et al., “Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges,” Information Fusion, vol. 58, pp. 82–115, 2020.
  17. P. Linardatos, V. Papastefanopoulos, and S. Kotsiantis, “Explainable AI: A review of machine learning interpretability methods,” Entropy, vol. 23, no. 1, p. 18, 2021.
  18. P. P. Angelov and E. A. Soares, “Towards explainable deep neural networks (xDNN),” Wiley Interdiscip. Rev.: Data Mining Knowl. Discov., vol. 10, no. 1, e1346, 2020.
  19. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proc. 31st Int. Conf. Neural Information Processing Systems (NeurIPS), 2017, pp. 4765–4774
  20. S. M. Lundberg et al., “Consistent individualized feature attribution for tree ensembles,” arXiv preprint arXiv:1802.03888, 2018.
  21. S. C. Tékouabou, Ș. C. Gherghina, H. Toulni, P. Neves Mata, and J. M. Martins, “Explainable machine learning models for customer churn prediction,” Mathematics, vol. 10, no. 14, p. 2379, 2022.
  22. S. S. Poudel, S. Pokharel, and M. Timilsina, “Explainable machine learning for customer churn prediction,” Machine Learning with Applications, vol. 14, 2024.
  23. UCI Machine Learning Repository, “Iranian churn dataset,” 2020. [Online]. Available: https://doi.org/10.24432/C5JW3Z
Index Terms

Computer Science
Information Sciences

Keywords

Customer churn prediction; Engagement features; XGBoost; Ensemble Learning; SHAP; Explainable AI

Powered by PhDFocusTM