Mahzad received her PhD in computer vision in 2009. She has over 10 years of experience in the field of data science, specializing in the implementation of data science and machine learning algorithms at scale. Additionally, she has worked on the application of reinforcement learning in video games for test automation. Currently, she is a Lead machine learning Specialist at Gearbox Studio Montreal.
Session
This presentation will be held in French
Machine learning, Data Science, AI in video games
Video games generate a vast amount of data every day, from various sources. One source is telemetry, which records all the actions and events performed by players in the game, such as quests completed, enemies defeated, and game times. In-game store purchases, whether made with virtual currency or real money, also generate data. Additionally, a significant amount of data is collected on the backend side for online and mobile games, such as breakdowns, connection numbers, and service alerts. Information related to social networks and discussion forums discussing the game also contributes to this wealth of data, which has only recently begun to be exploited. As a result, data science and machine learning teams have been created within studios to harness this data. In this presentation, we will provide an overview of the various applications of machine learning and data science in video game data. We will also discuss advances in AI, including applications of reinforcement learning. We will conclude this presentation with the challenges and issues relating to the democratization of machine learning within game productions.
