DeepMind and Liverpool FC develop AI to advise on football tactics
An AI model trained on data from Premier League matches can help football coaches devise tactics for attacking or defending corner kicks
By Matthew Sparkes
19 March 2024
Corner kicks, like this one taken by Trent Alexander-Arnold for Liverpool, can lead to goal-scoring opportunities
Robbie Jay Barratt/ AMA/Getty
An artificial intelligence model can predict the outcome of corner kicks in football matches and help coaches design tactics that increase or decrease the probability of a player taking a shot at goal.
Petar Veličković at Google DeepMind and his colleagues developed the tool, called TacticAI, as part of a three-year research collaboration with Liverpool Football Club.
Read more
The future of AI: The 5 possible scenarios, from utopia to extinction
Advertisement
Corner kicks are awarded when the ball goes out of play over the goal line, and can be a good scoring opportunity for the attacking team. Because of this, football coaches develop detailed plans for various scenarios, which players learn ahead of games.
TacticAI was trained on data from 7176 corner kicks in England’s 2020 to 2021 Premier League season, including each player’s position over time and their height and weight. It learned to predict which player would be the first to touch the ball after the corner kick was taken. In tests, the receiver of the ball was among TacticAI’s top three candidates 78 per cent of the time.
Coaches can use the AI to generate tactics for attacking or defending corners that maximise or minimise the chance of a certain player receiving the ball, and of a team being able to take a shot at goal. It does this by mining real examples of corner kicks for similar patterns, then offering suggestions for how to change the tactics to achieve the desired outcome.