Exploiting limited players’ behavioral data to predict churn in gamification
作者：
Highlights：
• A player churn prediction model using only information on in-game activity.
• Time investment (i.e., length and constancy of gameplay) is a predictor of churn.
• A function to embed information on improvement and worsening in in-game behaviors.
• An investigation on instance sampling methods and feature pre-processing.
• A visualization and interpretation of the prediction models with different settings.
摘要
•A player churn prediction model using only information on in-game activity.•Time investment (i.e., length and constancy of gameplay) is a predictor of churn.•A function to embed information on improvement and worsening in in-game behaviors.•An investigation on instance sampling methods and feature pre-processing.•A visualization and interpretation of the prediction models with different settings.
论文关键词：Gamification,Player experience,Churn prediction,Player behaviors
论文评审过程：Received 30 December 2019, Revised 23 April 2021, Accepted 26 April 2021, Available online 2 May 2021, Version of Record 17 May 2021.
论文官网地址：https://doi.org/10.1016/j.elerap.2021.101057
