A telecommunication company $($known as Telco company$)$ provides subscription$-$based telecommunication service, which is its major revenue source. In order to grow their revenue generating customer base, it is important for a Telco company to attract new customers as well as avoid termination of existing contracts, which is known as churn. Customer turnover, or churn rate, is the percentage of a company$$s customer base lost during a given period of time, usually on monthly or annual basis. A high churn rate may hurt revenue and profit badly. Many different reasons may trigger customers to terminate their contracts, such as better price offers and$/$or more interesting packages from competitors, bad service experiences, or change of customers$$ personal situations. In order to reduce churn rate, many Telco companies adopt a reactive approach: if a customer called with a request to cancel his or her contract, then the customer service representative would try to convince the customer to extend the contract, most often by offering free services or discounts on existing services. However, it would be more effective to estimate the probability that a given customer would churn in the near future, identify the factors that contributed most to that customer$$s decision, and then actively reach out to the customer to enhance his or her service experience and divert churn without giving up costly discounts. The goal of this project is to build a classification model using R to predict customer churn $($probability and classification$)$ for a Telco company.