Customer churn or Customer attrition is a serious issue in the telecommunication industry. Today, most of the companies in the telecom sector face this problem that leads them to lose revenue. To be successful in this business, the company has to acquire new customers or retain its users. Acquiring a new customer is significantly more expensive, ranging from five to seven times the cost of retaining an existing one. Retention of the customer is highly required for the company to continue to be successful in this highly competitive sector. As it directly shows an impact on the revenue, telecom companies are in search of new methods and strategies to minimize the switching of customers from one service provider to another and to increase the loyalty of the customers. We proposed a prediction model that helps these companies identify the churn of the customers and the reasons for the churn so that they can come up with new techniques that aid in the retention of the customers. The proposed model which is helpful in the early detection of the customers who are likely to churn uses efficient algorithms in machine learning such as Random Forest (RF) and Support Vector Machine (SVM). The telecom customer churn prediction model uses the most suitable approach and according to our experimental results, the model can achieve 95% accuracy with the Random Forest classifier algorithm.