METHOD OF CONTEXT-DEPENDENT XAI SELECTION FOR SAAS CUSTOMER CHURN PREDICTION

Abstract

This paper proposes a method for context-dependent selection of Explainable Artificial
Intelligence (XAI) methods for customer churn prediction in SaaS platforms. The proposed approach
systematizes XAI method selection based on two key dimensions: SaaS monetization model (Freemium, PLG,
Enterprise) and churn stage (Early, Mid, Late), forming the SXS-F framework in the form of a decision tree. A
comparative analysis of SHAP, LIME, DiCEML, and EBM methods across the proposed dimensions revealed
significant differences in fidelity, stability, and practical applicability depending on the context. The results
confirm the effectiveness of the context-dependent approach to XAI method selection for enhancing the
operational value of churn prediction systems in SaaS environments.
Keywords: churn prediction, XAI, explainable artificial intelligence, SaaS platforms, XAI method
selection, machine learning

References
1. Lakshmi A. J. та ін. Cloud Computing and Deep Learning for Customer Churn Prediction in
SaaS Platforms. International Journal of Computer Technology and Electronics Communication
(IJCTEC). 2026. Vol. 9, No. 1. P. 75–80. URL: https://doi.org/10.15680/IJCTECE.2026.0901012.
2. Gellanki G. N., Dasari K., Goona G. S., Alapana K. K. Customer Churn Prediction Using
Machine Learning. American Journal of Management and IOT Medical Computing. 2026. Vol. 5,
No. 1. P. 104–111. URL: https://www.ajmimc.com/.
3. Lundberg S. M., Lee S.-I. A unified approach to interpreting model predictions. Advances in
Neural Information Processing Systems (NeurIPS 2017). 2017. Vol. 30. P. 4765–4774. URL:
https://proceedings.neurips.cc/paper/2017/hash/8a20a8621978632d76c43dfd28b67767-
Abstract.html.
4. Özkurt C. Transparency in Decision-Making: The Role of Explainable AI (XAI) in Customer
Churn Analysis. Information Technology and Economics in Business. 2025. Vol. 2, No. 1. P. 1–11.
URL: https://doi.org/10.69882/ADBA.ITEB.2025011.
5. Ribeiro M. T., Singh S., Guestrin C. "Why should I trust you?": Explaining the predictions of
any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining. 2016. P. 1135–1144. URL: https://doi.org/10.1145/2939672.2939778.
6. Oprea S.-V., Bâra A. Customer-Centric Decision-Making with XAI and Counterfactual
Explanations for Churn Mitigation. Journal of Theoretical and Applied Electronic Commerce
Research. 2025. Vol. 20, No. 129. URL: https://doi.org/10.3390/jtaer20020129.
7. Adadi A., Berrada M. Peeking Inside the Black-Box: A Survey on Explainable Artificial
Intelligence (XAI). IEEE Access. 2018. Vol. 6. P. 52138–52160. URL:
https://doi.org/10.1109/ACCESS.2018.2870052.
8. Arrieta A. B., Díaz-Rodríguez N., Del Ser J. та ін. Explainable Artificial Intelligence (XAI):
Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion.
2020. Vol. 58. P. 82–115. URL: https://doi.org/10.1016/j.inffus.2019.12.012.
9. Shahabikargar M., Fabian L., Nesterenko V. та ін. A comprehensive survey on customer
churn analysis studies. Journal of Information and Telecommunication. 2023. Vol. 7, No. 1. P. 45–
72. URL: https://doi.org/10.1080/25765299.2023.2193636.
10.Wachter S., Mittelstadt B., Russell C. Counterfactual Explanations without Opening the Black
Box: Automated Decisions and the GDPR. Harvard Journal of Law & Technology. 2018. Vol. 31,
No. 2. P. 841–887. URL: https://doi.org/10.2139/ssrn.3063289.