Sevilla striker Isaac Romero celebrates his goal in the game against Girona last Sunday.David Borrat (EFE)
Sevilla's newest signing is not an everyday presence on the pitch: he doesn't run, defend or finish, and his physique is otherworldly. And yet the company is gaining ground and positioning itself as a key emerging player. This is artificial intelligence (AI), the use of which in sports will increase by 28.72% by 2026, according to the research company Mordor Intelligence. Teams such as the English Liverpool, the Spanish Valencia, the German Schalke 04, the Club América de Mexico Numerous teams in the major leagues of the United States already use it for new signings, analyzing the performance of athletes, developing training patterns, treating Injuries and identifying effective play patterns.
To enter this league of technology teams, Sevilla has partnered with IBM, one of the multinational corporations that, along with Microsoft and Google, are leading the artificial intelligence race. The club and the technology company have developed a tool based on a sports database with 200,000 reports that allows players to be selected based on their characteristics by interacting with the machine in natural language. “There are other clubs with more resources and that forces us to do things differently,” explains Elías Zamora, head of data at Sevilla.
The tool uses generative artificial intelligence, which can create unpublished content from complex databases with pre-training and a machine learning formula, unlike traditional systems that search limited sources and return limited results. The result is more precise and can be profiled or refined through direct dialogue with the machine.
When presenting the tool called Scout Advisor, which is designed to help select players based on the reports of Sevilla's scouts, artificial intelligence showed that they search the club's 200,000 reports in a matter of seconds and produce a list of footballers according to the requirements can create characteristics, with the identification of the team in which they play, their price, the expiration of the current contract, the percentage of similarity to the desired ideal and an average grade based on all the parameters used.
More information
Fernando Suárez, IBM program director, explains that signing a contract is one of the most complex actions for a club because it combines a high investment with a high level of uncertainty. “So far it has been based on people observing and analyzing a limited amount of data. “AI closes this gap.”
The result is cold. “Leadership or charisma are not recognized by the machine,” admits Suárez. Therefore, the final decision is human. “It is a source of information. Artificial intelligence wouldn’t have told us, “Sign up.” [Kylian] “Mbappé when he was 13 years old,” jokes Zamora, referring to the coveted PSG striker.
But Emilio de Dios, head of Sevilla scouts, believes it is a tool that has completely changed management: “We went from sailing to electricity. Reduces the search time from 500 hours to seconds. “It makes the final selection easier for us and allows us to select better players.” The first effective test will be in the transfer campaign for next season.
Risks
But the use of artificial intelligence in sports is not without risks. Alberto Carrio Sampredro, professor at Pompeu Fabra University and author of a legal and ethical framework for use in this area, warns in his research: “Manipulation of athletes and competitions are probably the most urgent. But there are others, such as the radical change in the governance of sports and sports competitions, which are entirely mediated by this disruptive technology.”
Javier Pérez Triviño, also from Peompeu Fabra, describes in another work the main threats of AI to athletes: the loss of autonomy over their performance, the inequality of those who do not have access to technology, the loss of the human element of sports practice, etc. Disruption in Comparison of performance and loss of excitement of competition. “AI can be accepted in sport, but in any case measures must be established to differentiate the nature of the improvements and to ensure respect for the primacy of natural talent in sporting achievements and equality,” he explains.
Fernando Suárez, head of the technology program at IBM, admits caution: “Not every type of AI is valid.” In this sense, the Seville program relies on the company’s WatsonX platform to ensure that the system is “open, precise “, scalable and controllable”.
Despite all caution, AI in sports, as in other areas, is experiencing strong growth. Liverpool were one of the first to use the services of DeepMind (Google) to help the coach make decisions.
Globant, LaLiga Tech and Microsoft have joined forces to develop projects related to football, basketball, rugby and tennis. Technology company Sparta Science uses AI to monitor athletes' physical critical points using a model that collects up to 3,000 pieces of data from athletes' bodies. The Cleveland Cavaliers (NBA) basketball team and the Colorado Rockies baseball team use it and claim to have reduced their players' injuries by almost 40%.
Second Spectrum programs help you evaluate individual and team performance and advise coaches on strategy decisions. The NBA has implemented systems to improve information for viewers with automated graphics.
In Formula 1, the association with the latest technological advances goes back to the origins of competition, and artificial intelligence from companies such as AWS (Amazon), Dell and Oracle is widely used in the development of racing strategies.
You can follow EL PAÍS technology on Facebook and X or sign up here to receive our weekly newsletter.
Subscribe to continue reading
Read without limits
_