A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games
A Semi-Supervised and Inductive Embedding Model for Churn Prediction of Large-Scale Mobile Games
复制标题
DOI：
10.1109/icdm.2018.00043
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
Xi Liu;Muhe Xie;Xidao Wen;Rui Chen;Yong Ge;N. Duffield;Na Wang
中科院分区：
文献类型：
--
作者：
Xi Liu;Muhe Xie;Xidao Wen;Rui Chen;Yong Ge;N. Duffield;Na Wang
移动的游戏已成为一个充满希望的市场，收入达数十亿美元。各种各样的移动的游戏平台和服务已经在世界各地被开发。这些平台和服务面临的一个关键挑战是了解手机游戏中的用户流失行为。准确的流失预测将使许多利益相关者受益，如游戏开发商，广告商和平台运营商。在本文中，我们提出了第一个大规模的流失预测解决方案的手机游戏。鉴于建立在传统机器学习模型基础上的最先进方法的共同局限性，我们设计了一种新的半监督和归纳嵌入模型，该模型联合学习用户-应用关系的预测函数和嵌入函数。我们通过具有独特边缘嵌入技术的深度神经网络对这两个功能进行建模，该技术能够捕获上下文信息和关系动态。我们还设计了一个新的属性随机游走技术，同时考虑到拓扑邻接和属性相似性。为了评估我们的解决方案的性能，我们从Samsung Game Launcher平台收集了真实数据，其中包括数万款游戏和数亿次用户与应用程序的交互。这些数据的实验结果表明，我们提出的模型对现有的最先进的方法的优越性。
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.