One of the U.K.’s finest soccer clubs is making history by using a new AI assistant developed by Google DeepMind to help with its tactics.

It’s not unusual for soccer teams to analyze plays, but Liverpool might be ahead of the pack when it comes to using machine-learning technology to figure out tactics. The club and DeepMind have been collaborating for about three years now, with the upshot being the release of TacticAI.

The system works by analyzing corner kicks, the set play given after the ball goes out of play, and the other team is given a chance to kick the ball from the corner toward the goal. Such kicks and how players move near the goal are a matter of extensive planning based on the firepower of the forwards and the quality of the defense. Where the player taking the kick aims the ball is often based on the other team’s defensive weaknesses.

From 2020 to 2021, TacticAI was trained on data from 7,176 corner kicks that were taken throughout the Premier League season. Using predictive and generative AI, TacticAI learned to predict where the ball would go, and it was very good at it, making the right prediction 78% of the time.

“We developed and evaluated TacticAI together with experts from Liverpool Football Club as part of a multi-year research collaboration,” DeepMind said in a press release today. “TacticAI’s suggestions were preferred by human expert raters 90% of the time over tactical setups seen in practice. TacticAI demonstrates the potential of assistive AI techniques to revolutionize sports for players, coaches, and fans.”

There’s a good chance that the fans – people not always receptive to new technologies on the soccer field – may turn their noses up at such technology, but if it starts to work for one club, the other clubs may have no choice but to follow. Welcome to the future. On its website, TacticAI hails itself as a “revolution in sports.”

TacticAI’s powers, said DeepMind, can be applied to more areas of the game than corner kicks. The company said it could be used for all set plays or even general play throughout the game. Petar Veličković, a staff research scientist at Google DeepMind, said the technology could also be adopted by football, hockey or basketball teams.

“Top clubs are always searching for an edge, and I think our results indicate that techniques like these are likely going to become a part of modern football going forward,” Veličković told MIT Technology Review. “As long as there’s a team-based sport where you believe that modeling relationships between players will be useful and you have a source of data, it’s applicable.”

Photo: Jan Solo/Flickr