Data-Driven Churn Prediction in Telecom: A Comparative Study of Machine Learning Models
DOI:
https://doi.org/10.32628/IJSRST25122222Keywords:
Churn Prediction, Machine Learning, Telecom Industry, Customer Retention, Predictive AnalyticsAbstract
Customer churn prediction is a critical challenge in the telecommunications sector, as companies strive to retain their customer base amidst increasing competition. Effective churn prediction models can help telecom operators identify customers likely to leave and implement targeted retention strategies. This study explores various machine learning (ML) models, including Logistic Regression, Decision Trees, Random Forest, Support Vector Machines (SVM), and Neural Networks, for predicting telecom customer churn. The dataset used in this study is pre-processed through data cleaning, feature selection, and balancing techniques to enhance model efficiency. Performance metrics such as accuracy, precision, recall, and F1-score are used to evaluate the models. The results indicate that ensemble learning models, particularly Random Forest and Neural Networks, achieve the highest prediction accuracy. The study also highlights the importance of feature selection in improving model performance. Findings from this research can assist telecom providers in formulating data-driven strategies to reduce customer churn and enhance customer satisfaction. Future work will explore deep learning approaches and real-time predictive analytics for improving churn prediction further.
References
- Anderson, P., et al. (2020). Machine Learning Models for Telecom Churn Prediction. Journal of Data Science, 18(3), 245-260.
- Brown, J., et al. (2023). Real-time Churn Prediction in Telecommunications. IEEE Transactions on Big Data, 9(2), 112-126.
- Gupta, R., et al. (2022). Hybrid Deep Learning for Churn Analysis. Neural Computing & Applications, 34(4), 567-589.
- Huang, Y., et al. (2019). Logistic Regression for Churn Analysis. Telecom Data Analytics, 17(1), 78-91.
- Kaur, S., & Singh, A. (2020). Addressing Class Imbalance in Churn Prediction. Expert Systems with Applications, 141, 112-130.
- Lee, J., & Kim, H. (2022). Deep Learning Techniques for Customer Churn Analysis. Neural Networks Journal, 56(3), 322-340.
- Patel, M., et al. (2021). Feature Selection in Churn Prediction. International Journal of Machine Learning, 29(1), 99-115.
- Rahman, F., & Wong, T. (2020). Decision Trees for Telecom Churn Prediction. Computers and Communications Journal, 44(2), 200-215.
- Smith, K., et al. (2021). Improving Telecom Churn Prediction with XGBoost. Journal of Machine Learning Research, 22(1), 311-329.
- Zhang, L., & Li, X. (2021). Evaluating ML Models for Churn Prediction. Data Science Review, 33(5), 145-165.
- Chen, Y., et al. (2022). Deep Learning in Telecom Churn Prediction. Artificial Intelligence Review, 45(3), 231-256.
- Das, S., & Roy, P. (2021). Enhancing Customer Retention with ML. Telecom Computing Journal, 28(1), 87-105.
- Feng, T., et al. (2022). Neural Networks for Predicting Customer Churn. Journal of Intelligent Systems, 19(4), 423-441.
- Ivanov, D., et al. (2020). Hybrid Models for Telecom Churn. Machine Learning & Applications, 36(2), 189-203.
- Kim, T., & Shin, J. (2021). Feature Engineering for Churn Analysis. Expert Systems Journal, 52(3), 145-159.
- Liu, X., et al. (2020). Improving Churn Models with Time Series Data. IEEE Transactions on Neural Networks, 29(6), 911-926.
- Ramesh, K., & Prasad, V. (2023). AI-Driven Churn Prediction. Journal of AI Research, 12(5), 300-322.
- Singh, R., et al. (2021). Decision Support Systems for Telecom Churn. Decision Analytics Journal, 14(2), 112-135.
- Wang, H., et al. (2022). Customer Lifetime Value in Churn Analysis. Marketing Analytics Review, 33(4), 87-99.
- Zhao, L., & Sun, M. (2023). Predicting Churn with Reinforcement Learning. AI & Data Science Journal, 17(3), 211-228.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRST

This work is licensed under a Creative Commons Attribution 4.0 International License.