Increasingly, educational games have become an established part of the instructional landscape, however designing a compelling and effective instructional game remains a challenge. One of the reasons for this challenge is that game players are afforded some agency to craft their own experiences, making it difficult to anticipate the kinds of experiences they might have. Further, when designing with an instructional intent the goal is to make a lasting impact on players' knowledge, which is invisible to designers.
In my work, I look to address these challenges by developing novel tools and processes to provide designers with different perspectives on player experience. By drawing from varied backgrounds of HCI, Data Science, and Artificial Intelligence, I build models of players that can be compared to real player behavior and provide data to decide whether a game is playing according to its intention. In this talk I will describe several projects that support this goal and layout my vision for educational game design as a data-informed craft.