Multi-Domain Customer Churn Prediction using Transfer Learning

Customer Churn Prediction is a task that analyses or identifies the customers who are likely to stop using the product,service,or subscription in the near future using data analytics and machine learning techniques. By analyzing customer behavior, transaction history, and engagement metrics, businesses can proactively intervene to retain at-risk customers, thereby reducing revenue loss and improving customer lifetime value. This project focuses on multi-domain churn prediction using transfer learning, which enables knowledge transfer from data-rich domains to data-scarce domains to improve the prediction accuracy. This study aims to improve churn prediction accuracy across multiple domains using transfer learning. For example, telecom dataset(data-rich) and data-scarce domains may be like new streaming services or new bank services. In this approach, the model is pre- trained on a known large labeled source dataset to learn customer behavior patterns. This model then fine-tuned on a smaller target domain dataset, optimizing for specific churn indicators in the new domain. The results demonstrate that the it shows better prediction accuracy and generalization compared to the models trained on the target dataset, the transfer learning improves churn prediction performance in data-scarce by learning the knowledge from the data-rich domains. By enabling accurate churn prediction across different industries and also assisting businesses in reducing customer churn and improving long-term customer retention.

Customer-Churn prediction, Transfer learning, cross-domain learning, neural networks, Explainable AI,Banking Analytics, Telecom Analytics

1. Asif, D., Arif, M. S., & Mukheimer, A. (n.d.). A data-driven approach with explainable artificial intelligence for customer churn prediction in the telecommunications industry. A data-driven approach with explainable artificial intelligence for customer churn prediction in the telecommunications industry.2025 [Google Scholar] [Crossref]

2. Babu, C. B., Krishnan, G.H., & S.Prabhu. (n.d.). Enhancing Accuracy in Spatial Satellite Image Classification through Transfer Learning and Model Ensemble. Enhancing Accuracy in Spatial Satellite Image Classification through Transfer Learning and Model Ensemble.2022 [Google Scholar] [Crossref]

3. Bo, G. D., Milan, G. S., & Toni, D. D. (n.d.). Proposal and validation of a theoretical model of customer retention determinants in a service environment. Proposal and validation of a theoretical model of customer retention determinants in a service environment.2020 [Google Scholar] [Crossref]

4. De, S., Prabu, P., & Paulose, J. (n.d.). Application of Machine Learning in Customer Churn Prediction. Application of Machine Learning in Customer Churn Prediction. [Google Scholar] [Crossref]

5. https://ieeexplore.ieee.org/document/9696771.2024 [Google Scholar] [Crossref]

6. Gaur, A., & Dubey, R. (n.d.). Predicting Customer Churn Prediction. Predicting Customer Churn Prediction In Telecom Sector Using Various Machine Learning Techniques. [Google Scholar] [Crossref]

7. https://ieeexplore.ieee.org/document/8933783.2026 [Google Scholar] [Crossref]

8. Geetha S, Arunesh S S, Balahariharan S, Thangaraj, R., Deepa B, & Sowmiya M. (n.d.). Prediction of Bank Customer Churn for Retention Strategies Using Machine Learning. Prediction of Bank Customer Churn for Retention Strategies Using Machine Learning. 2018 [Google Scholar] [Crossref]

9. Gupta, V., Liao, W.-. K., Choudhary, A., & Agrawal, A. (n.d.). Combining Transfer Learning and Representation Learning to Improve Predictive Analytics on Small Materials Data. Combining Transfer Learning and Representation Learning to Improve Predictive Analytics on Small Materials Data.2025 [Google Scholar] [Crossref]

10. Mingdady, A., Alnatesheh, A., & AIZoubi, O. (n.d.). Machine Learning Algorithms for Customer Churn Prediction in Telecoms Sectors. Machine Learning Algorithms for Customer Churn Prediction in Telecom Sectors.2016 [Google Scholar] [Crossref]

11. Nadeem, L., Ramachandran, C. R., & Rajeswari, M. (n.d.). Customer churn prediction in the telecommunication industry using machine learning models.2015 [Google Scholar] [Crossref]

12. Rahman, M. S., Alam, M. S., & Hosen, M. I. (n.d.). To Predict Customer Churn By Using Different Algorithms. To Predict Customer Churn By Using Different Algorithms.2024 [Google Scholar] [Crossref]

13. Shaaban, E., K. Helmy, Y., Ayman Elsayed, & Nasr, M. M. (n.d.). A Proposed Churn Prediction Model. A Proposed Churn Prediction Model.2024 [Google Scholar] [Crossref]

14. Tsai, T. -Y., Lin, C. -T., & Prasad, M. (n.d.). An Intelligent Customer Churn Prediction and Response Framework. An Intelligent Customer Churn Prediction and Response Framework. [Google Scholar] [Crossref]

15. Xiao, J., Jiang, X., He, C., & Teng, G. (n.d.). Churn Prediction in Customer Relationship Management via GMDH-Based Multiple Classifiers Ensemble. Churn Prediction in Customer Relationship Management via GMDH-Based Multiple Classifiers Ensemble.2012 [Google Scholar] [Crossref]

16. Xie, L., Li, D., & Xiao, J. (n.d.). Feature selection based transfer ensemble model for customer churn prediction. Feature selection based transfer ensemble model for customer churn prediction.2018 [Google Scholar] [Crossref]

17. Zhu, J., Teng, W., & Wang, H. (n.d.). Interpretable Customer Churn Prediction Model with Sparse Differential Feature Learning and Graph Attention. Interpretable Customer Churn Prediction Model with Sparse Differential Feature Learning and Graph Attention.2019 [Google Scholar] [Crossref]

• Self-Supervised Learning for Oil Spill Detection in Synthetic Aperture Radar Imagery
• Graph Neural Networks to Detect Suspicious Patterns in Nigerian Elections