\n<\/p>\n
Sevilla F\u00fatbol Club (Sevilla FC), based in the southern Spanish city of Seville, are seven-time Europa League champions.\u00a0<\/span><\/p>\n 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 \u2013 Sevilla FC have over 300,000 scouting reports to use for recruiting new players \u2013 they need a way to turn that information into real-world talent.\u00a0<\/span><\/p>\n To analyze and make use of their soccer talent data, Sevilla FC\u2019s data department partnered with IBM to create Scout Advisor, a generative AI-driven scouting tool designed and built on watsonx, IBM\u2019s portfolio of AI products, with Meta\u2019s Llama 3.1 70B Instruct model.\u00a0<\/span><\/p>\n \u201cScout Advisor uses Llama 3.1 70B Instruct\u2019s advanced natural language processing to bridge the gap between qualitative human insights and quantitative data analysis,\u201d says Elias Zamora, Chief Data Officer (CDO) for Sevilla FC. \u201cThis 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.\u201d<\/p>\n 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.<\/p>\n Now Sevilla FC\u2019s recruiters can simply ask Scout Advisor a question about the soccer talent they\u2019re looking for to see a list of matching players, including precise AI-generated summaries of their performance. IBM\u2019s watsonx and Meta\u2019s Llama enable Sevilla FC to bridge the gap between traditional human-centric and data-driven scouting in the identification and characterization of potential recruits. <\/em><\/p>\n 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.<\/p>\n Built with IBM\u2019s watsonx and leveraging Llama, Scout Advisor is able to comprehend soccer-industry terms and answer questions accurately.<\/p>\n 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\u2019s scouting reports.<\/p>\n For example, a simple query like \u201cshow me talented wings\u201d<\/em> automatically gets refined with soccer-specific information, so that search results look right: \u201cA talented wing takes on defenders with dribbling, creating space and penetrating the opposition.\u201d<\/em><\/p>\n In contrast, a general-purpose model\u2019s response might include irrelevant results, like a chicken wing recipe.<\/p>\n \u201cWe selected Llama 3.1 70B for its text enrichment and summarization performance, particularly in the Spanish language,\u201d Zamora says.<\/p>\n 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.<\/p>\n \u201cThis is a revolutionary tool for a football director. I don\u2019t need to review 45 reports for a player to know what my scouting department thinks of them,\u201d says Victor Orta, Sporting Director at Sevilla FC. \u201cIn perhaps two minutes, I can get all the information that I need to make a decision.\u201d<\/p>\n For those inspired by their AI initiatives, Zamora says it\u2019s 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\u2019s capabilities, helping them keep their leading edge in sports AI.<\/p>\n<\/p><\/div>\nMaking Scouting Report Searches Easier<\/h2>\n
Learning to Talk Soccer<\/h2>\n
Strong Results for Scout Advisor<\/h2>\n