Euro 2024 is a valuable source of data for AI researchers
During the EURO 2024, huge amounts of data will be generated, which Prof. Daniel Link will use to create forecasts and analyses with AI methods
(Image: alphaspirit.it / Shutterstock.com)
The research team led by Professor Daniel Link from the Technical University of Munich (TUM) is using machine learning to analyze match data from Euro 2024. They aim to use artificial intelligence (AI) to recognize complex tactical constructs such as pressing or counter-pressing and to estimate in which situations which style of play is successful.
The team uses three different data sources. They record match results such as passes, shots on goal and tackles manually using data loggers. Optical methods are also used: several cameras record the pitch and recognize the movements of the players and the ball in the video image. At Euro 2024, the ball itself will also be fitted with a sensor.
Multiple data sources for AI sports analysis
The mix of AI and sport is particularly appealing to Link. "AI is particularly suitable for solving complex classification problems. Sport is an fascinating field of application because human behavior is studied here in a natural, highly competitive environment that is also reduced in complexity by the rules", says Link.
Predicting match results, as with the ChatGPT European Championship Oracle, is not in the research group's remit. According to the researchers, soccer will always remain unpredictable and determined by elements of chance. The scientific analysis of match data makes it possible to evaluate performance indicators such as running performance, passing rates and duel statistics. "Data helps to better understand individual aspects and control training loads. We are only at the beginning when it comes to using this data comprehensively," Link is convinced.
(dmk)
