AI football manager knows how different teams play the game
Be unpredictable to win (Image: Gabriel Pecot/AP/PA)
WHO really calls the shots in team sports? The players? The coach? Maybe it could be a computer.
Software analysis of the passing strategies of teams in the Spanish football league during the 2013-14 season has given a unique insight into how they play. It’s one of a raft of artificial intelligence tools that are giving coaches a deeper understanding of the game.
The software analysed video of 300,000 passes made across the season and identified hundreds of patterns used by the teams.
“We were curious about whether it was possible to distil some of the tactics of the team from the trajectory of the ball,” says Laszlo Gyarmati of the Qatar Computing Research Institute.
Sure enough, the algorithm revealed that Barcelona and Real Madrid had over 100 recurring passing patterns – 151 and 180 respectively. There were surprises, too. Atlético Madrid, which won the league that season, had just 31 recurring patterns (arxiv.org/abs/1508.02171).
“Atlético Madrid had just 31 recurring passing patterns, a lack of predictability that made them so successful”
Stefan Szymanski, a professor of sport management at the University of Michigan, says this lack of predictability could be why Atletico Madrid were successful.
Source: AI football manager knows how different teams play the game
Via: Google Alerts for AI