Abstract - In today’s highly competitive telecom sector, customer churn — the loss of clients to competitors — poses a major threat to revenue and growth. This project tackles churn prediction using machine learning, focusing on the Random Forest algorithm to identify customers likely to leave. The Telco Customer Churn dataset, containing customer demographics, service usage, and account details, serves as the foundation.The workflow begins with exploratory data analysis (EDA) to uncover key trends and indicators of churn. A robust preprocessing pipeline is then applied, including handling missing data, encoding categories, scaling, and addressing class imbalance. Random Forest is chosen for its accuracy and interpretability, and its performance is compared against models like Logistic Regression, SVM, and XGBoost using metrics such as precision, recall, F1-score, and ROC-AUC.Results show that contract type, tenure, and billing-related features significantly influence churn. The model not only predicts churn with high accuracy but also provides actionable insights through feature importance and visualization tools. This supports data-driven retention strategies like targeted offers or improved services.Ultimately, the project showcases how machine learning enhances customer relationship management (CRM) and can be adapted for similar use cases in banking, insurance, and e-commerce. Key Words: Customer churn, churn prediction, Random Forest, machine learning, telecom industry, predictive modeling, supervised learning