Sevilla Fútbol Club (Sevilla FC), based in the southern Spanish city of Seville, are seven-time Europa League champions.
Talent scouting in the Europa League is competitive, so Sevilla FC have worked to stay ahead. And with more data in their hands than ever before – Sevilla FC have over 300,000 scouting reports to use for recruiting new players – they need a way to turn that information into real-world talent.
To analyze and make use of their soccer talent data, Sevilla FC’s data department partnered with IBM to create Scout Advisor, a generative AI-driven scouting tool designed and built on watsonx, IBM’s portfolio of AI products, with Meta’s Llama 3.1 70B Instruct model.
“Scout Advisor uses Llama 3.1 70B Instruct’s advanced natural language processing to bridge the gap between qualitative human insights and quantitative data analysis,” says Elias Zamora, Chief Data Officer (CDO) for Sevilla FC. “This fusion enhances the efficiency and effectiveness of our scouting operations, ensuring that our recruitment strategies are both data-driven and deeply informed by human expertise.”
Making Scouting Report Searches Easier
To make recruiting decisions, Sevilla FC needed to assess qualities like attitude, tenacity and leadership across a large volume of scouting reports. Without Scout Advisor, recruiters had to spend 200 to 300 hours analyzing a single shortlist of players.
Now Sevilla FC’s recruiters can simply ask Scout Advisor a question about the soccer talent they’re looking for to see a list of matching players, including precise AI-generated summaries of their performance. IBM’s watsonx and Meta’s Llama enable Sevilla FC to bridge the gap between traditional human-centric and data-driven scouting in the identification and characterization of potential recruits.
Having such an effective operation for scouting players has helped Sevilla FC attract talent, while generating opportunities from other teams who want to use AI for help.
Learning to Talk Soccer
Built with IBM’s watsonx and leveraging Llama, Scout Advisor is able to comprehend soccer-industry terms and answer questions accurately.
Through prompt enrichment, Scout Advisor automatically optimizes questions to get the best possible results from the AI solution. Prompt enrichment ensures that soccer-specific questions give the agent enough context for a thorough analysis of Sevilla FC’s scouting reports.
For example, a simple query like “show me talented wings” automatically gets refined with soccer-specific information, so that search results look right: “A talented wing takes on defenders with dribbling, creating space and penetrating the opposition.”
In contrast, a general-purpose model’s response might include irrelevant results, like a chicken wing recipe.
“We selected Llama 3.1 70B for its text enrichment and summarization performance, particularly in the Spanish language,” Zamora says.
Strong Results for Scout Advisor
Since implementing Scout Advisor, Sevilla FC have improved their scouting process with shorter evaluation time, enhanced talent identification, a stronger competitive edge and new consulting opportunities and revenue streams.
“This is a revolutionary tool for a football director. I don’t need to review 45 reports for a player to know what my scouting department thinks of them,” says Victor Orta, Sporting Director at Sevilla FC. “In perhaps two minutes, I can get all the information that I need to make a decision.”
For those inspired by their AI initiatives, Zamora says it’s crucial to have a solid data foundation, deep business understanding and a well-educated team. In the future, Sevilla FC plans to evaluate new versions of Llama to keep refining Scout Advisor’s capabilities, helping them keep their leading edge in sports AI.