We present a deep learning framework for game action modeling, which enables fine-grained analyses of player behavior. We develop CNN-based supervised models that effectively learn the critical game play decisions from skilled players, and use these models to assess player characteristics in the system, such as their retention, engagement, deposit buckets, etc. We show that with a carefully constructed input format, that efficiently represents the game state and history as a multi-dimensional image, along with a custom architecture the model learns the strategies of the game accurately. It is further enhanced with look-ahead achieved by self-play simulation to better estimate the game state, and this information is used in a new loss function. Next, we show that analyzing the players with these models as reference has immense benefit in understanding player potential in terms of engagement and revenue. We also use the model to understand the various contexts under which players tend to make mistakes, and use these insights to up-skill players.

Database applications such as enterprise resource planning systems and customer relationship management systems are widely used software systems. Development and testing of database applications is difficult because the program execution depends on the persistent state stored in the database. In this paper we show that how versioning of the persistent data stored in the database can solve some critical problems in the development and testing of database applications can be solved by versioning the data stored in the database. Our solution framework is based on long transaction management, a well-researched branch of database systems. We also present empirical results that show the proposed framework's effectiveness in practice.