Can I read Predicting Dota 2 Outcomes with ML on EtoBox?

Predicting Dota 2 Outcomes with ML by Jair Polanco is a document available to read on EtoBox.

What is Predicting Dota 2 Outcomes with ML about?

This thesis examines using machine learning techniques to predict the winning team in Dota 2 games based on partial game state data. Random forest is identified as the best performing algorithm with an average accuracy of 88.83% in predicting outcomes, including 82.23% accuracy at the five minute point of games. The results indicate that machine learning can accurately predict Dota 2 results in real-time as the game progresses based on parsed replay data.

Author

Jair Polanco

Language

EN