Enhancing game customer churn prediction with a stacked ensemble learning model

Although some machine learning methods have been widely applied to customer churn prediction across various fields, few studies have focused on customer churn in card and board mobile games. Moreover, the massive volume of game log data presents new challenges for customer churn prediction. To address this, this paper proposes a customized high-performance solution based on the big data technology, Spark. Initially, Spark is utilized to preprocess the game log data and compute features; subsequently, the neighborhood cleaning rule (NCL) method is employed to handle the issue of class imbalance; finally, an ensemble learning model based on the stacking method is constructed. We validated our approach on a large-scale real dataset (260 GB). The results show that the method proposed in this paper performs optimally, achieving an accuracy of 96.33%, and the entire solution takes only 11 min to execute, meeting the practical requirements for prediction accuracy and data processing capability.