Sevilla FC transforms player recruitment with Watsonx generative AI
IBM and Sevilla FC have introduced Scout Advisor, a generative AI tool to help the Spanish soccer club adtopt a data-driven approach to talent identification and evaluation.
Built on Watsonx, Sevilla FC’s Scout Advisor will integrate with the platform’s existing suite of self-developed data-intensive applications.
Sevilla’s data department worked with IBM’s client engineering team to build Scout Advisor, leveraging Watsonx’s natural language processing (NLP) and foundation models to search and analyse massive amounts of information present in the club’s databases to evaluate potential recruits. This includes both quantitative data such as height and weight, speed, number of goals or minutes played, and qualitative unstructured data such as the textual analysis contained in their more than 200,000 scouting reports.
The solution has enabled Sevilla to use multiple large language models (LLMs) to help enhance the accuracy and effectiveness of their player identification. Using prompts from Sevilla scouters describing the key characteristics of the players searched, Scout Advisor generates curated lists of candidates based on stated requirements and summarises the full set of scouting reports for each individual player. Additionally, it also links every player to the Sevilla’s own data-applications to obtain deep insights about their quantitative performance figures.
Player scouting and recruiting decisions at elite sports teams involve multi-million dollar investments, long-term contracts and high levels of uncertainty on performance and return on investment. Player recruitment has traditionally relied on a combination of subjective human observation and manual data analysis. This approach has several limitations as it is both time-consuming and considers only a limited number of factors.
An aid, not a substitute
Scout Advisor offers Sevilla further competitive advantage of combining their existing capabilities with the use of generative AI to bridge the gap between metrics-based scouting and human-centric observations that cannot be as easily measured on the pitch.
TechCentral.ie, in an exclusive interview with Elías Zamora Sillero, chief data officer of Sevilla Football Club, explained how the club’s scouts integrate the new technology. “So, the scouts have to keep evaluating players,” he said. “This is what I see because I’m the engineer, let’s say I try to bring information, then how would it convert into business?
“Right now, the scout watches a match, they evaluate the player and they store it in some kind of file that I then download and install in my data lake. Then the idea is to have people in the sports department that are able to ask the right questions. So to be able to provide this Scout Advisor on similar platforms that we already have in the club.
“Ideally, a scout should be able to specify criteria like ‘I want a player in the centre forward position with over 1,000 minutes played in the Bundesliga or the Premier League from Portugal. The player should cost less than €10 million and score more than five or 10 goals per season.’ The recruitment experts are responsible for formulating and assessing these precise questions.”
Sillero went on to explain, that the platform will not replace the scouting process as we know it. Intangibles like the ability to work in a team or deal with pressure situations remain core to the role.
“These kinds of things are typically much better or much easier to assess by a human than by a machine,” said Sillero. “The ability to be a leader with human qualities is crucial. In football, playing alongside someone can elevate their performance. Leadership that instils genuine belief in the team’s abilities, is vital. These are elements that I typically include in a scouting report, that are not easily derived from cameras tracking players on the field. Human assessment excels in understanding these nuances, something machines have not mastered well yet. Hence, the importance of combining both subjective and objective data for us.”
Also present at the event José María del Nido Carrasco, president, Sevilla FC, added: “Our team of scouters and analysts is committed to finding the best players to support our team’s success and have worked tirelessly to build an impressive database of player reports, and now, with the support of IBM, we can utilise this asset to its full potential. This gives us a significant advantage in the player recruitment process and enables us to find the best players for our team and continue to improve our performance on the pitch. We believe that this collaboration will have a positive impact not only for Sevilla FC but for the sports industry as a whole. With this tool, Sevilla FC also demonstrates that technology is not just a goal but an intimate companion on the journey towards the future of our entity; it is part of its DNA.”
TechCentral Reporters
Subscribers 0
Fans 0
Followers 0
Followers