Customer Propensity Prediction in E-Commerce Loyalty Program

This paper presents a model that has been developed to predict customers'; propensity to subscribe to Hepsiburada';s loyalty program, Hepsiburada Premium. Hepsiburada, a leading e-commerce platform in Turkey, aims to enhance customer loyalty by offering various benefits to its customers. In this model, data obtained from Hepsiburada';s active customers is being used to predict the likelihood of subscribing to the Premium program. This model considers demographic characteristics, shopping history, customers'; website behavior and specific features of the Premium program. Based on predictions obtained using the XGBoost algorithm, different campaigns are offered to customers. This model demonstrates that machine learning can be an effective tool for identifying potential customers for loyaltyprograms and campaigns.