Blizzard Entertainment has partnered with IBM to use Artificial Intelligence (AI) to find the best Overwatch players in the world. Both companies have signed a multi-year partnership to use AI-based solutions and knowledge to analyze players and rank the most skilled players in the Overwatch League sports tournament.
IBM formed a six-member team for this project that began in September 2020. This Area 631 team has the brightest minds in IBM with a background in the IBM, Watson, and AutoAI cloud. IBM in a blog post explained that the game collected more than 360 player performance statistics during each action step.
Overwatch is a first-person shooter (FPS) game in which two teams fight. Each team has six players with two members assigned to a role each. There are three main functions for a team in Overwatch, which include damage, tanks, and support. The main task here is for players to have dozens of characters to choose from for each role.
“These are statistics on the performance of the tank, the support and the damage of a character that focus largely on adding the totals and determining the rates of return that is based on the total time of the action step (ie , total healing, total healing, healing per second, and healing every 2 seconds), “IBM said in a blog post.
Candidate high-level architecture for OWL power ratings (IBM)
In total, there are 1.8 million data points in a game, 18 million data points each week of the regular season and 410 million data points per season. These are the raw data that was provided to the IBM team for further analysis to determine the most qualified players. IBM will begin publishing its results for the 2021 Overwatch League season in the coming weeks.
It has already produced results for the Overwatch League 2020 season which took place last September. Interested parties can view Overwatch’s current global rankings via this link.