Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{187612,
        author = {R. Anisha and Shravani G and Mithan Gowda M K and Manogna R and B Uma},
        title = {Customer Churn Prediction Model},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {6383-6387},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187612},
        abstract = {Client retention really matters in today’s telecom world. It’s expensive to win new customers, and honestly, people can switch providers pretty easily now. When customers leave—what we call churn—it hits a telecom company right where it hurts: profits and long-term stability. We set out to build a machine learning model that could spot when customers were ready to leave. We looked at everything—how long they'd been around, what kind of contract they had, their monthly bills, internet details, even how often they called tech support. The Telco Customer Churn Dataset gave us a good starting point, but honestly, it wasn't enough. So we made our own custom dataset, adding features that really captured what we wanted to dig into. Getting the data ready took some work. We coded the categories, filled in missing spots, and normalized the numbers so everything lined up for training. Then tried out several classification methods—Logistic Regression, Random Forest, and XGBoost. We didn’t just run the models; we dug into how each one performed and what worked best.},
        keywords = {Customer Churn Prediction, Machine Learning, telco dataset, Data preprocessing, Ensemble models, SMOTE, SHAP, Telecom analytics, Predictive Modelling.},
        month = {November},
        }