Year of Graduation
Application of Machine Learning Methods to Analysis of Cyber-Sport Events
Applied Mathematics and Information Science
In this paper, we present a novel approach of ranking individual player's impact based on their contribution in team victory. The work was focused on Dota 2 ESport discipline. Every single player was represented by role, which he performed in a corresponding team. Such a representation allows us to make use of machine learning methods and a history of professional matches for estimating each team player influence on team victory/defeat. TrueSkill model was used to establish a lower bound for the accuracy of winning team prediction.