A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games
This addresses the problem of user churn prediction for stakeholders like game developers and platform operators in the mobile gaming industry, representing an incremental improvement over existing methods.
The paper tackles churn prediction in mobile games by proposing a semi-supervised and inductive embedding model that jointly learns prediction and embedding functions using deep neural networks with edge embedding and attributed random walk techniques, achieving superior performance on real-world data from the Samsung Game Launcher platform with tens of thousands of games and hundreds of millions of interactions.
Mobile gaming has emerged as a promising market with billion-dollar revenues. A variety of mobile game platforms and services have been developed around the world. One critical challenge for these platforms and services is to understand user churn behavior in mobile games. Accurate churn prediction will benefit many stakeholders such as game developers, advertisers, and platform operators. In this paper, we present the first large-scale churn prediction solution for mobile games. In view of the common limitations of the state-of-the-art methods built upon traditional machine learning models, we devise a novel semi-supervised and inductive embedding model that jointly learns the prediction function and the embedding function for user-app relationships. We model these two functions by deep neural networks with a unique edge embedding technique that is able to capture both contextual information and relationship dynamics. We also design a novel attributed random walk technique that takes into consideration both topological adjacency and attribute similarities. To evaluate the performance of our solution, we collect real-world data from the Samsung Game Launcher platform that includes tens of thousands of games and hundreds of millions of user-app interactions. The experimental results with this data demonstrate the superiority of our proposed model against existing state-of-the-art methods.