Application of Machine Learning in the Telecommunications Industry: Partial Churn Prediction by using a Hybrid Feature Selection Approach

The telecommunications industry is one of the most competitive industries in the world. Because of the high cost of customer acquisition and adverse effects of customer churn on the company's performance, customer retention becomes an inseparable part of strategic decision-making and one of the main objectives of customer relationship management. Although customer churn prediction models are widely studied in various domains, several challenges remain in designing and implementing an effective model. This paper attempts to address the customer churn prediction problem with a practical approach. The experimental analysis was conducted on the actual customers' data gathered from available data sources at a telecom company in Iran. First, the partial churn was defined in a new way which exploits the status of customers based on the criteria that can be measured easily in the telecommunications industry. Moreover, a hybrid feature selection approach was proposed in which various feature selection methods, along with the wisdom of the crowd, were applied. It was found that the wisdom of the crowd can be used as a useful feature selection method. Finally, a predictive model was developed using advanced machine learning algorithms such as bagging, boosting, stacking, and deep learning. The partial customer churn was predicted with more than 88% accuracy by the Gradient Boosting Machine algorithm by using 5-fold cross-validation. Comparative results indicate that the proposed model performs efficiently compared to the ones applied in the previous studies.