|The present Sri Lankan telecommunication industry remains extremely dynamic by constantly changing the landscape of new services, technologies, and carriers. Thus customers have more choices. So, predicting customer churn is one of the most challenging targets in the telecommunication industry today. The major aim of the study is to develop a novel customer churn prediction model for Sri Lankan Telecommunication Company by considering some soft factors for early identification of customers who leave the service provider. Three machine learning algorithms namely Logistic Regression, Naive Bayes and Decision Tree are used in this study. In fact, twenty attributes are mainly carried out to train these three algorithms. Furthermore, the Back Propagation Neural Network (BPNN) was trained to predict customer churn. In Artificial Neural Network (ANN) training; result of Logistic Regression, Naive Bayes and Decision Tree and eight attributes that mostly affecting the final result are used as inputs. The performances of the models are evaluated by using the confusion matrix using three different data samples. Final ANN model gives 96.7% accuracy in the testing process. Also it gives a high accuracy when comparing with the other data mining algorithms. Existing customer churn prediction models are designed using single algorithm. But the experimental results in this study show multiple algorithms for churn prediction that give higher performance than a single algorithm.