Search academic texts

Information × Registration Number 2124U004714, Article popup.category Препринт Title popup.author Kosyk Daryna popup.publication 01-01-2024 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4844 popup.publisher Description In recent years, there has been a noticeable increase in the adoption of subscription- based monetization models within the mobile app industry, emphasizing the im- portance of accurately predicting essential product metrics associated with this ap- proach. A critical metric in this regard is the customer retention rate, which indicates customer satisfaction and significantly impacts companies’ financial and marketing strategies. Among various customer retention prediction methods, those based on probability distributions are notable for their effectiveness and simplicity. How- ever, each method has its strengths and weaknesses. This thesis explores the ef- ficiency of probabilistic models, specifically the Shifted-Beta-Geometric (sBG) and Beta-Discrete-Weibull (BdW), in predicting customer retention rates using both trial and non-trial subscription data from different mobile apps. Our research aims to implement, refine, and evaluate these models to determine the optimal use cases for their applications across various business contexts. We show that the proposed combined approach is superior to the solitary one. popup.nrat_date 2025-05-09 Close