Death prediction in DOTA 2 using Deep Learning
Adam Katona, Ryan Spick, Victoria Hodge, Simon Demediuk, Florian Block, Anders Drachen, James Alfred Walker
Esports have become major international sports with hundreds of millions of spectators and they generate massive amounts of telemetry data. Micro-predictions, which seek to predict events inside a match, are of perennial interest across esports commentators and audience.
In this project, we used deep learning network with shared weights which provides accurate death predictions within a five-second window. This model enables real-time micro-predictions of kills in Dota 2, one of the most played esports titles in the world, giving commentators and viewers time to move their attention to these key events.
Contact us
Professor Richard Wilson
Artificial Intelligence Research Group lead
Contact us
Professor Richard Wilson
Artificial Intelligence Research Group lead