The effects of digital strategies on customer churn in the telecom industry

Abstract

The telecom industry has been saturated over the last years and organic growth in the number of customers has been slowing down. Institutions allocate a significant amount of resources to reducing churn rates as the variations in service offerings become subtle. Customer retention strategies such as customer relationship management, loyalty programs, and convergence of services are some of the widely-used efforts in the telecom industry in this respect. Thanks to the increasing app penetration, digital loyalty apps, and over-the-top media services emerged as a way of both service differentiation points as well as customer retention strategies. Regardless of all these strategies, some customers will still churn; therefore, churn prediction plays an essential role in the sustainable future of businesses. Churn prediction is used both to detect customers with a high propensity to churn and to interpret the reasons behind the churn decision of customers. This study examines the variables playing important role in churn decisions and the effectiveness of digital loyalty and over-the-top service strategies on customer retention in light of the relationship marketing strategy. The customer churn data in this study is received from a telecom company and contains the attributes of both churner and non-churner customers. Random Forest and Logistic Regression classifiers are used as the machine learning algorithm in the churn prediction model. To understand the variable importance, mean decrease in impurity and mean decrease in model accuracy using permutation are used. The key findings of this research revealed that while digital loyalty app strategies are effective, over-the-top media service strategies play an unimportant role in the churn decision of customers.