According to developers of IBM, Now overwatch will use AI to collect More than 1.8M data points in any given match you join and process this data to build power rankings.
For those of you who are not much familiar with Overwatch, Overwatch is an intense 6v6, network-based, action game that is played by millions of gamers in over 190 countries.
The game challenges teams to capture more objectives than their opponents against the backdrop of fantasy cityscapes, using an array of tools and characters.
The fast-paced and chaotic nature of the game has made ranking players by performance a difficult task until now.
Recently, The maker of overwatch, Blizzard Entertainment joined forces with IBM to develop a new data-driven system for ranking the best Overwatch players in the world using the help of AI and machine learning.
According to an IBM Developers blog post, the Overwatch Power Rankings will be based on upwards of 360 performance metrics (damage per second, healing, weapon accuracy, etc.), with roughly 1.8 million data points collected in any given match.
It means the game will collect 360+ player performance statistics during each action step.
Here is the amount of data AI will collect of your games:
- 1.8M data points in a match
- 18M data points each week of the regular season
- 410M data points per season
These data will all be aggregated, arranged, and then analyzed to determine if any correlations exist between particular in-game actions and the outcome of the match.
IBM will apply machine learning techniques to this dataset to determine which metrics best reflect players’ quality. Although all available metrics will contribute to final rankings, the pool of roughly 30 metrics will have a major impact on player positioning.
According to Jon Spector, Vice President of Overwatch Esports at Blizzard, “while esports pundits are able to draw on a wealth of knowledge to provide context for viewers, the new system contributes additional color to analysis that would otherwise be impossible.”
“We’ve got really talented analysts that follow our players and teams, but there is so much happening in these matches, no human being could possibly observe and evaluate it all,” he said.
“We needed a way to capture and analyze every move from every player and feed all that insight into a ranking system that was totally objective and reliable.”
After Implementing this overwatch AI for building power rankings, overwatch players would get better rankings according to their performance.