Telecom Customer Chum Prediction based on Half Termination Dynamic Label and XGBoost

Abstract

With the rapid progress of the telecom industry and fierce competition among telecom operators, telecom companies pay more attention to customer retention. Telecom companies developed multiple solutions to predict churn customers before customers move to another telecom operator. However, the existing prediction solutions have some disadvantages in the real-world use cases. For example, churn definition is limited to moving from one telecom operator to another, which is too late for preventing customer churn. The main contribution of the paper is to introduce the new definition of customer chum for the telecom industry, and to propose a Half Termination Dynamic Label (HTDL) that improves the churn prediction solution with XGBoost. Experiment results showed that the proposed solution improved the model performance, which significantly outperforms traditional solution, in terms of churn prediction on F1-score. The new solution also sidelines more active customers for retention.