2D-ATT: Causal Inference for Mobile Game Organic Installs with 2-Dimensional Attentional Neural Network

In the mobile gaming industry, organic installs refer to downloads that cannot be attributed to any advertising channel and thus do not introduce upfront user acquisition (UA) cost. Understanding the causal factors on organic installs is of vital importance for a game's ecosystem, as such knowledge can help bring in more organic users, who tend to be more loyal and active. A major challenge in discovering the causal effects is the potential temporal lag between an UA operation and the growth in organic installs. In this paper, we solve the problem by using a deep attentional neural network to analyze multivariate time series data. The core of our design is a novel attention mechanism, namely 2D-ATT, that can learn the contribution of each feature to the target at different levels of temporal delay. Our experiments on a series of synthetic datasets show that 2D-ATT outperforms existing approaches for discovering complex causal effects. We also use 2D-ATT to analyze a real-world mobile game dataset collected by Jam City, a video game company based in California. Our discoveries provide valuable insights to UA operations.