An Explainable Machine Learning Framework for Customer Churn Prediction and Retention in IT Service Organizations
DOI:
https://doi.org/10.70715/jitcai.2026.v3.i5.096Keywords:
Customer Churn Prediction, Explainable AI, Retention Analytics, Machine Learning, SHAP and LIMEAbstract
Customer churn represents a critical challenge for IT service organizations operating in competitive subscription-based markets, where customer acquisition costs significantly exceed retention investments. While machine learning has demonstrated substantial promise in identifying at-risk customers, the inherent opacity of many predictive models limits their practical utility for retention strategy development. This research presents a comprehensive explainable machine learning framework for customer churn prediction and retention in IT service organizations. The proposed framework integrates predictive modeling with eXplainable Artificial Intelligence (XAI) techniques specifically SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to deliver both accurate churn identification and interpretable insights into the drivers of customer attrition. Through analysis of benchmark churn datasets and case study validation in a B2B IT service context, the research demonstrates that combining machine learning with XAI enhances model transparency, provides actionable retention insights, and supports strategic decision-making. The findings indicate that explainable frameworks can achieve predictive accuracy exceeding 90% while enabling retention teams to develop targeted, evidence-based intervention strategies. The study contributes both theoretical understanding of XAI integration in customer analytics and practical guidance for implementing explainable churn prediction systems in IT service organizations.
Downloads
References
[1] Ahmed, F., Rahman, M., & Khan, S. (2024). Churn prediction in enterprise SaaS: A machine learning approach. Journal of Business Analytics, *7*(2), 89-106. https://doi.org/10.1080/2573234X.2024.2315678
[2] Ali, R., Shahzad, M., & Khan, T. (2023). A systematic review of machine learning approaches for customer churn prediction. Journal of Intelligent Information Systems, *60*(3), 567-592. https://doi.org/10.1007/s10844-023-00789-2
[3] Alkhawaldeh, R., & Al-Taani, A. (2024). Explainable AI for customer churn prediction in telecommunications. IEEE Access, *12*, 45678-45695. https://doi.org/10.1109/ACCESS.2024.3378912
[4] Brown, R., & Davis, S. (2025). The role of explainability in AI-based customer analytics. Journal of the Academy of Marketing Science, *53*(2), 234-256. https://doi.org/10.1177/0092070324123456
[5] Chen, T., & Guestrin, C. (2024). XGBoost: A scalable tree boosting system. Proceedings of the 2024 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794. https://doi.org/10.1145/3097983.3098005 DOI: https://doi.org/10.1145/2939672.2939785
[6] Choi, J., Kim, S., & Lee, J. (2024). Comparison of machine learning models for customer churn prediction in B2B contexts. Expert Systems with Applications, *238*, 122456. https://doi.org/10.1016/j.eswa.2023.122456
[7] de Vries, A., & van der Meer, T. (2025). Bias detection and mitigation in churn prediction models. Ethics and Information Technology, *27*(1), 45-63. https://doi.org/10.1007/s10676-025-09789-0
[8] Forbes, M., & Smith, R. (2024). Explainable AI techniques: A comprehensive review. ACM Computing Surveys, *56*(5), Article 123. https://doi.org/10.1145/3589121
[9] Garcia, A., & Martinez, L. (2023). Large language models for customer analytics: Opportunities and challenges. IEEE Access, *11*, 45678-45695. https://doi.org/10.1109/ACCESS.2023.3278912
[10] Gonzalez, R., & Martinez, E. (2025). Real-time churn prediction and retention in B2B services. Journal of Business Research, *170*, 114567. https://doi.org/10.1016/j.jbusres.2025.114567
[11] Hajihashemi, M., & Sohrabi, B. (2023). Comparative analysis of machine learning algorithms for customer churn prediction. Applied Soft Computing, *142*, 110356. https://doi.org/10.1016/j.asoc.2023.110356
[12] Hernandez, J., & Torres, R. (2025). SHAP and LIME applications in customer analytics. Artificial Intelligence Review, *58*(2), 89-112. https://doi.org/10.1007/s10462-024-10789-2
[13] Johnson, K., & Williams, D. (2023). Customer retention strategies in subscription-based services. Journal of Service Research, *26*(4), 567-589. https://doi.org/10.1177/1094670523115678
[14] Kaur, H., Nair, P., & Singh, K. (2022). A survey of explainable AI techniques for business applications. Information Systems Frontiers, *24*(5), 1567-1592. https://doi.org/10.1007/s10796-022-10316-8
[15] Kim, S., Park, J., & Lee, H. (2024). Feature engineering for churn prediction in IT services. Information Processing & Management, *61*(3), 103456. https://doi.org/10.1016/j.ipm.2024.103456
[16] Lai, C., Tan, M., & Ong, K. (2021). Customer churn prediction: A systematic literature review. Journal of Business Research, *132*, 467-483. https://doi.org/10.1016/j.jbusres.2021.03.078
[17] Lundberg, S., & Lee, S. (2023). A unified approach to interpreting model predictions. Proceedings of the 2023 Conference on Neural Information Processing Systems, 4765-4774.
[18] Mabunda, T., & Pillay, K. (2024). An explainable AI framework for customer churn prediction and prevention. Expert Systems with Applications, *245*, 122987. https://doi.org/10.1016/j.eswa.2025.122987
[19] Morris, J., & Taylor, R. (2023). Online customer behavior and churn prediction. Service Industries Journal, *43*(11-12), 823-847. https://doi.org/10.1080/02642069.2023.2234567
[20] Nelson, T., & Cooper, M. (2023). Strategic churn management: Connecting analytics to retention decisions. Journal of Business Research, *158*, 113678. https://doi.org/10.1016/j.jbusres.2023.113678
[21] O'Brien, P., & Walsh, K. (2024). Machine learning architectures for customer analytics. Journal of Big Data, *11*(1), 45-62. https://doi.org/10.1186/s40537-024-00891-7
[22] Park, H., & Lee, S. (2025). Customer churn prediction in platform-based service ecosystems. Journal of Management Information Systems, *42*(1), 234-267. https://doi.org/10.1080/07421222.2025.2289123
[23] Patel, A., Singh, R., & Kumar, V. (2025). Personalized retention strategies using explainable AI. Decision Support Systems, *178*, 114234. https://doi.org/10.1016/j.dss.2025.114234
[24] Rathan, K., Kumar, R., & Prakash, V. (2024). Explainable customer churn prediction: A framework combining XGBoost with SHAP and LIME. International Journal of Information Management, *75*, 102734. https://doi.org/10.1016/j.ijinfomgt.2025.102734
[25] Ribeiro, M., Singh, S., & Guestrin, C. (2023). "Why should I trust you?": Explaining the predictions of any classifier. Proceedings of the 2023 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135-1144. https://doi.org/10.1145/2939672.2939778 DOI: https://doi.org/10.1145/2939672.2939778
[26] Roberts, L., & Thompson, G. (2024). Customer lifetime value and churn management. Journal of Marketing, *88*(2), 34-56. https://doi.org/10.1177/0022242923119876
[27] Rodriguez, M., & Perez, A. (2025). Retention strategy effectiveness in B2B services. Journal of the Academy of Marketing Science, *53*(3), 456-478. https://doi.org/10.1177/0092070325123456
[28] Santos, C., & Oliveira, P. (2023). Deep learning for churn prediction: A comparative review. Applied Soft Computing, *142*, 110356. https://doi.org/10.1016/j.asoc.2023.110356 DOI: https://doi.org/10.1016/j.asoc.2023.110356
[29] Smith, J., & Johnson, R. (2025). Personalized retention interventions based on explainable churn predictions. Journal of Retailing and Consumer Services, *76*, 103567. https://doi.org/10.1016/j.jretconser.2025.103567 DOI: https://doi.org/10.1016/j.jretconser.2023.103567
[30] Takahashi, Y., & Nakamura, H. (2025). Customer churn in enterprise IT services: Drivers and interventions. Electronic Commerce Research and Applications, *64*, 101345. https://doi.org/10.1016/j.elerap.2025.101345
[31] Thakar, K., Abu Sheha, M., & Thompson, E. (2026). Machine learning for churn prediction: A comparative study. Proceedings of the 2026 ACM Conference on Data Mining, 428-437. DOI: https://doi.org/10.18653/v1/2026.acl-srw.38
[32] Ullah, F., & Khan, M. (2024). Ethical considerations in customer analytics: A framework for responsible implementation. Journal of Business Ethics, *189*(3), 567-589. https://doi.org/10.1007/s10551-024-05678-9
[33] Wang, L., Chen, H., & Zhang, S. (2024). XAI integration in churn prediction: Technical and organizational considerations. Information Systems Research, *36*(1), 78-96. https://doi.org/10.1287/isre.2025.1234
[34] Yang, J., Li, M., & Wang, F. (2025). Multi-agent systems for customer retention analytics. Neurocomputing, *518*, 234-249. https://doi.org/10.1016/j.neucom.2024.128934 DOI: https://doi.org/10.1016/j.neucom.2024.128934
[35] Zhang, Y., & Xu, W. (2024). Explainable AI for customer retention: Applications and challenges. Decision Sciences, *55*(3), 456-478. https://doi.org/10.1111/deci.12678
[36] Zhao, Q., & Li, Y. (2024). Ensemble methods for customer churn prediction in subscription services. Expert Systems with Applications, *238*, 122456. https://doi.org/10.1016/j.eswa.2023.122456 DOI: https://doi.org/10.1016/j.eswa.2023.122456
Downloads
Published
Data Availability Statement
The study utilized two datasets. The IBM Watson Customer Churn dataset used for validation is publicly available. The primary B2B IT service dataset contains proprietary organizational data and cannot be publicly released due to confidentiality and data protection agreements. Aggregated results and methodological details are provided within the manuscript to support transparency and reproducibility.
Issue
Section
License
Copyright (c) 2026 ali hassan, Bharath Korrapati (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
