Çağlıyor, SendiKirgiz, Omer BugraKiygi-Calli, MeltemCagliyor, SendiEl Oraiby, Maryam2024-10-152024-10-15202400308-59611879-3258https://doi.org/10.1016/j.telpol.2024.102816https://hdl.handle.net/20.500.12469/6348Kiygi-Calli, Meltem/0000-0002-2979-9309Telecom operators allocate a significant amount of resources to retain their customers as the organic growth in the number of customers is slowing down. Gamified loyalty programs, branded apps, and over-the-top (OTT) services emerged as ways to develop customer acquisition and retention strategies. Despite these strategies, some mobile customers still churn; therefore, churn prediction plays an essential role in the sustainable future of telecom businesses. Churn prediction is used both to detect customers with a high propensity to churn and to identify the reasons behind their churn behavior. This study examines several features affecting the churn behavior of mobile customers, including branded apps, gamified loyalty programs, and OTT services. In this study, the secondary data is provided by a telecom operator and contains the attributes of both churner and non-churner mobile customers. Logistic regression and random forest classifiers are compared in terms of their predictive power, and we used the latter as the machine learning algorithm in the churn prediction model. To understand the variable importance, mean decrease in impurity and permutation importance are performed. The key findings of this research reveal that while gamified loyalty giveaways and branded app strategies are effective, OTT service strategies show lower importance in predicting mobile customer churn behavior.eninfo:eu-repo/semantics/closedAccessChurn predictionOver-the-top (OTT) servicesMachine learningTelecom operatorGamified loyalty giveawaysBranded appsArticle848WOS:00129899540000110.1016/j.telpol.2024.1028162-s2.0-85196965369Q1Q1