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 insights to analyze players and rank the most skilled players in the Overwatch League esports tournament.
IBM formed a team of six for this project, which started in September 2020. This Area 631 team has IBM’s best minds with backgrounds in IBM cloud, Watson and AutoAI. IBM explained in a blog post that the game collects more than 360 player performance statistics during each action step.
Overwatch is a first person shooter (FPS) game in which two teams compete against each other. Each team has six players with two members each assigned one role. There are three main roles for a team in Overwatch, and these include damage, tank, and support. The main task here is that players can choose from dozens of characters for each role.
These are statistics about a character’s role performance from tank, support, and damage that are largely focused on aggregating totals and determining achievements based on the total time of the action step (i.e., total heals, total heals , healing per second and healing per 2 seconds), ”said IBM in a blog post.
High Level Candidate Architecture for OWL Power Rankings (IBM)
In total there are 1.8 million data points in a match, 18 million data points per week of the regular season and 410 million data points per season. This is the raw data provided to the IBM team for further analysis to determine the most skilled players. IBM will begin publishing the results for the Overwatch League 2021 season in the coming weeks.
It has already yielded results for the Overwatch League 2020 season that took place in September last year. Those interested can view Overwatch’s current global rankings via this link.