Data scientist Farzain Majeed has published an algorithm called DeepLeague, and a training dataset, capable of watching footage of the video game League of Legends and tracking player movements, similar to how sports analytics systems would convert player actions on the field to data. The dataset consists of 100,000 labeled images Majeed generated of League of Legends characters moving around the game map. Majeed made DeepLeague and its data freely available as open source to encourage the development of analytics systems for esports.
Training AI to Analyze Esports
Joshua New is a senior policy analyst at the Center for Data Innovation. He has a background in government affairs, policy, and communication. Prior to joining the Center for Data Innovation, Joshua graduated from American University with degrees in C.L.E.G. (Communication, Legal Institutions, Economics, and Government) and Public Communication. His research focuses on methods of promoting innovative and emerging technologies as a means of improving the economy and quality of life. Follow Joshua on Twitter @Josh_A_New.
View all posts by Joshua New