Predicting Customer Churn in Telecommunication Services Using Machine Learning

Customer churn occurs when users stop using a service, and is a serious headache for telecommunication companies. To tackle this, we dove into machine learning techniques, specifically Artificial Neural Networks (ANN) and Long Short-Term Memory (LSTM) models, to predict churn patterns. Our study is based on an online survey, gathered via Google Forms, that captures various aspects, including demographics, service usage, and satisfaction levels. We applied machine learning techniques like ANN and LSTM, to evaluate the churn trends.
Our study shows that LSTM outshines ANN when it comes to accuracy. These insights can be helpful to telecommunication providers to define actionable strategies to improve customer retention and build stronger relationships with their user base.

Customer Churn, Artificial Neural Networks, Long Short-Term Memory, Sentiment Analysis.

1. Verbeke, W., Martens, D., Mues, C., &Baesens, B. "Building comprehensible customer churn prediction models with advanced rule induction techniques." Proceedings of the International Conference on Expert Systems with Applications. Elsevier, 2011. [Google Scholar] [Crossref]

2. Qureshi, S. A., Rehman, A. S., Qamar, A. M., Kamal, A., & Rehman, A. "Telecommunication subscribers’ churn prediction model using machine learning." Proceedings of the Eighth International Conference on Digital Information Management. IEEE, 2013. [Google Scholar] [Crossref]

3. Hutto, C. J., & Gilbert, E. "VADER: A parsimonious rule-based model for sentiment analysis of social media text." Proceedings of the International AAAI Conference on Web and Social Media. AAAI Press, 2014. [Google Scholar] [Crossref]

4. Larose, D. T., & Larose, C. D. Discovering knowledge in data: An introduction to data mining (2nd ed.). Wiley, 2014. [Google Scholar] [Crossref]

5. Amin, A., Anwar, S., Adnan, A., Nawaz, M., Alawfi, K., Hussain, A., & Huang, K. "Customer churn prediction in the telecommunication sector using a rough set approach." Proceedings of the International Conference on Neurocomputing. Elsevier, 2016. [Google Scholar] [Crossref]

6. Goodfellow, I., Bengio, Y., & Courville, A. Deep learning. MIT Press, 2016. [Google Scholar] [Crossref]

7. Ahmed, A. A., & Maheswari, D. "Churn prediction on huge telecom data using hybrid firefly-based classification." Proceedings of the Egyptian Informatics Journal Conference. Elsevier, 2017. [Google Scholar] [Crossref]

8. Kotu, V., & Deshpande, B. Data science: Concepts and practice (2nd ed.). Morgan Kaufmann, 2019. [Google Scholar] [Crossref]

9. Kim, H., & Yoon, C. "LSTM-based churn prediction model for telecommunication customers." Proceedings of the IEEE Access Conference on Machine Learning and Data Science. IEEE, 2020. [Google Scholar] [Crossref]

10. Zhang, Y., Zhang, Y., & Zhang, M. "Sentiment analysis for customer churn prediction in telecommunications." Journal of Big Data Proceedings. Springer, 2022. [Google Scholar] [Crossref]

11. Ross, T. J. Fuzzy logic with engineering applications. John Wiley & Sons, 2023. telecommunication churn prediction [Google Scholar] [Crossref]

12. A public dataset repository for telecommunication churn prediction, useful for benchmarking your 600-response dataset. [Google Scholar] [Crossref]

• A Machine Learning Model for Predicting the Risk of Developing Diabetes - T2DM Using Real-World Data from Kilifi, Kenya
• AI-Powered Facial Recognition Attendance System Using Deep Learning and Computer Vision
• A Comprehensive Review on Brain Tumour Segmentation Using Deep Learning Approach
• A Scalable Retrieval-Augmented Generation Pipeline for Domain-Specific Knowledge Applications
• Predictive Maintenance in Semiconductor Manufacturing Using Machine Learning on Imbalanced Dataset