CUSTOMER CHURN PREDICTION MODEL USING MACHINE LEARNING

ABSTRACTCustomer attrition poses a major issue for the telecommunications sector, resulting in revenue declineand higher expenses for gaining new customers. Predicting churn accurately enables telecomcompanies to take instant measures for retention of customers. This study leverages specificallyRandom Forest, Decision Tree, and XG-Boost, to develop a robust and accurate churn predictionmodel. These algorithms analyse customer behavioural data, including call duration, internet usage,billing history, and complaints, to identify potential churners. Decision Tree provides an interpretablemodel, Random Forest improves predictive accuracy through ensemble learning, and XG-Boostenhances performance with gradient boosting and optimized handling of imbalanced datasets. Theproposed model assists telecom companies in classifying customers based on their churn risks,enabling the implementation of targeted retention approaches like tailored discounts and rewardsprograms. By integrating advanced machine learning techniques, telecom service providers canenhance customer retention, minimize the churn rates, and improves the business sustainability. Thestudy highlights the importance of decision making based on data in the telecom sector, demonstratinghow predictive analytics can optimize customer relationship management and drive profitability Keywords: Predicting customer churn, different machine learning techniques, Random Forestalgorithm, Decision Tree method, XG-Boost model, retention of customers, analytics for forecasting,gradient boosting techniques, telecom sector.