Always-online video games are rapidly transforming the video game industry. They entail complex and interesting problems, and the actions performed by their players generate extremely rich datasets that constitute an ideal playground to understand human behavior. Data-driven game development has extraordinary potential both to provide players with an optimized game experience and to increase user engagement.

Machine learning methods can be used to predict individual player behavior, revealing information such as the moment and game level at which a certain player will leave the game, or when she will make her next purchase and which virtual item she is likely to select. This allows developers to take preventive actions aimed at maximizing player lifetime.

I will review the main artificial intelligence techniques that will revolutionize the video game industry, focusing on deep learning methods that are crucial to provide a customized player experience through personalized game events, marketing campaigns, and in-game item/action recommendations. Then, I will discuss how these methods can make predictions in an operational environment, thanks to their ability to deal with really big datasets (petabytes of data) and easily adapt to different kinds of games and players.

This is an entry level talk about Game Data Science.

Takeaway: 

- See how Machine Learning can predict when players will leave the game, how much they will spend, and which items they will purchase next. 

- Learn how operational predictions and analytics can help game development and operation.