NEWS
PLAYER RESOURCES | April 22, 2026
Embedded Files
AI in Sports is Inevitable
Glasgow City forward Nicole Kozlova knew what she wanted in her next football team before landing at the Scottish club: possession, chance creation, a place for her to flourish. Plenty of teams promised that. But Kozlova could do one better; she corroborated their claims using artificial intelligence (AI).
In addition to being a footballer, Kozlova works as a data analyst with Twelve Football, an analytics company started five years ago that now incorporates artificial intelligence (AI) via a machine-learning system. She has worked with the technology to enhance her decision-making, something companies like Twelve think could benefit women’s football as a whole.
In a world increasingly being shaped by and responding to AI, football is no exception. At the top end of the men’s game, recruitment and scouting headquarters can resemble a Silicon Valley tech start-up more than a club’s data department. AI can help with forecasting injury-risk, improving set-play defending or analyzing key performance indicators as granular as the degree to which a player leans back for a free kick.
Last week, Chelsea announced a multi-year global partnership with Industrial AI company IFS, adding that the partnership would also see the company’s AI technology embedded into “football performance, operational excellence and fan engagement”, according to the club’s statement.
While IFS’s partnership with Chelsea includes the women’s team, in general, women’s football’s relationship with AI remains limited compared to the men’s game.
A key reason is access to the data AI needs. Where there is limb-tracking technology in the men’s game, the women’s game, even at the very top, still suffers from inaccuracies, such as the number of yellow cards or assists. Collection remains limited to event data, or on-the-ball actions, and is reliant on the availability of cameras on pitches and in training sessions, something that not every women’s team or league can provide.
Kozlova’s story sits at a uniquely opposite juncture.
Presented with the possibility of signing with Glasgow City in the Scottish Premier League in the summer of 2024, Kozlova, who was finishing playing with Ukraine top-flight side Vorskla Poltava, dug into the numbers.
Glasgow’s previous season (2023-24) represented one of the team’s worst in recent history. Having won 15 of the previous 16 SWPL titles, the Champions League regulars finished the season nine points adrift of Rangers and Celtic, the latter of which won the title on goal difference.
However, the numbers told a more nuanced story. Glasgow City created high-quality chances and prioritised possession, as they promised; they had just failed to do so against the top two sides.
“Teams can advertise what style they play or how they want to play, but it can be a completely different picture if you look into it,” says Kozlova. “I brought it up with them. They said they knew, but in the previous season, the trends were more positive. And the data backed it up.”
Kozlova moved to Scotland. She finished her first season as the club’s top goal scorer with 23 across all competitions. Glasgow finished second in the league, three points behind champions Hibernian.
This season, Glasgow, who now use Twelve Football for their match and scouting analytics, sit top of the table, five points clear of Celtic and Rangers.
For Kozlova, the experience was a flex of agency and self-empowerment in a space where players and clubs existing outside the upper echelons struggle to compete. Last year, Kozlova helped a friend assess the underlying numbers of a club trying to sign her. The data showed a club considerably over-performing their xG. “I told her this seemed like a club that in six months would have their luck run out.” In six months, it did.
Indeed, below the upper echelons of the international and domestic game, which suffer from limited scouting networks, inchoate infrastructure and access to agents, autonomy and visibility can feel like rare currencies.
“Visibility is one of the biggest challenges in women’s football right now,” says Kozlova, who created a presentation to showcase not only her skills but also to analyse precisely the gaps in which Glasgow City needed her. “Those smaller leagues, the clubs that aren’t the 15 competing in the Champions League and some national teams aren’t getting as much visibility.
“The data helps build your case and argue that potentially, you could be given a chance if you’re not one of the big names or one of the big clubs.”
Lifting the playing field is a common thread running through the arguments for utilising AI in the women’s game.
“We have a lot of contact with women’s teams from bigger clubs and small clubs,” says Markus Lådö, the co-founder of Twelve. “They really see AI as an opportunity of getting analytics that are really advanced without having the resources. The top clubs, when it comes to the Premier League, most of them have their own kind of data science department, but on the women’s side, it’s different.”
According to Lådö, how Twelve works with clubs varies.
Advanced packages include adapting the learning models to the type of play or recruitment strategy clubs want to implement, with the AI answering back. These can span multiple seasons or years to be focused on a specific endgame, such as a major tournament.
Twelve has also developed an AI-powered analytics tool, dubbed Earpiece, which analyses vast global match data and delivers the complex information into a simple, legible message via WhatsApp. More akin to ChatGPT, it enables clubs to explore the strengths and weaknesses of a player or even request shortlists of certain attributes, initially without a number in sight, as if chatting to a coach or a sporting director.
This method of operation is not without controversy. Last year, Seattle Reign FC head coach Laura Harvey ignited a fierce diatribe around the use of AI when she admitted on a podcast to using ChatGPT during the 2025 NWSL season to brainstorm tactics and formations (even leading her to decide to field a back five in two matches).
Harvey’s admissions led to many fans and pundits criticising her for normalising outsourcing expertise to technology at a time when opportunities for women coaches and analysts remain at a premium and when women’s setups are asking clubs to invest more in infrastructure and staff numbers.
As The Athletic reported last year, the transformational effects of AI could threaten the future of traditional scouting, with many fearful of losing their jobs.
According to Twelve, the cost of their AI technology for a year can span anything from €25 (£22, $30) per month for access to its generative AI program to €9,000 per year for personalised projects. It is far less than a club might spend on hiring a full-time data analyst or a scout.
Ida Höglund Persson, head of decision science at Twelve, says that for many women’s football clubs that don’t boast intricate scouting networks or sentries of in-house data analysts, technology such as Earpiece can be an invaluable margin bender.
“It differs that you don’t need a data scientist who actually does the programming because that’s the first step for football clubs is to hire one data scientist, and they are stuck with trying to deliver everything to the club,” says Persson.
Instead, Persson argues, Twelve does the laborious grunt work for the data scientists, allowing them to become more active in working with the insights from the data itself, delivering it to the club and the organisation as opposed to being bogged down in the programming and presentations themselves.
“Then they can spend the time actually working on the insights and what to do with them,” she says.
Clubs who have worked with Twelve include both the men’s and women’s teams at Hammarby, the latter with whom Twelve began working in 2017, as they re-entered the Swedish top flight. Hammarby have since twice won the league while finishing runners-up last season and developed young players who have made lucrative moves to the Women’s Super League (WSL), including forward Ellen Wangerheim (Manchester United), forward Cathinka Tandberg (Tottenham Hotspur) and full-back Smilla Holmberg (Arsenal).
Pablo Pinones-Arce, now the head coach of Fiorentina, was the head coach of Hammarby from 2020 to 2023, taking the club from a seventh-place finish in his first season to winning the club’s first league title since 1995 in his last.
“I don’t use AI in the way people might think,” he says. “I don’t ask AI what to do for a match or how to set up my team. I have my principles, my ways of working.”
Pinones-Arce says he uses AI to “confirm what I see with my eyes”, from identifying players and identifying strengths and weaknesses of his own team. AI, he says, has never been a charter to which he or staff cede, nor should it be.
“If you want to develop the women’s side in a professional environment, you should have the circumstance and the environment to try to make the best out of what you have,” he says.
“Staff needs to be bigger. You need specialists and experts in different areas. But AI could be a helpful tool as many others, if you don’t have the right economic circumstances to actually have people working there, as long as you know why you’re using it, how you’re using it, and what you expect from it.”
There are critical elements of sport that simply cannot and should not be outsourced to technology, Pinones-Arce says. Data cannot measure work ethic, mindset or tenacity. While it might be able to forecast how a player adapts to the physicality of a league, it cannot forecast how that same player interacts with teammates or adapts to new environments, countries or cultures.
“One of the most important things as a coach is to have the right leadership, the right approach to leadership, the right approach to development, to developing players and to actually be there for the players’ sake,” says Pinones-Arce.
“You can never replace going to the stadium, watching a player live.”
Critics warn that not every club sees AI as a supplement instead of a substitute.
According to numerous data analysts and club figures spoken to for this piece, who wished to remain anonymous to protect relationships, there is a worry that rather than build the foundational infrastructure needed for recruitment or tactical analysis with qualified staff and resources and using AI as a tool to help streamline, clubs are tempted to rely solely on the AI to compensate for a lack of resources.
The soft skills that come with data science roles are where analysts truly earn their money, evaluating the strengths and weaknesses of certain analyses to form their own conclusions. The limitations of data available in the women’s game also means there is a risk of bias or fragmented perspective if analysts are not available to interrogate the data themselves.
According to Persson, data for Twelve is still largely collected by humans who are watching video from available cameras in stadiums and on training pitches. These insights are mostly event data, which focuses on on-ball actions. Off-ball runs, runs in behind, second assists, and many defensive actions can be missed or overlooked, creating incomplete versions of a player.
AI becoming part of the everyday fabric of football is one of the core ambitions of Twelve. The impact of removing barriers to technology should not be underestimated. In this way, Persson underscores AI’s equalising potential in women’s football, a tool that raises the ceiling but more crucially the floor of the game.
“I think in five years, everyone will use this as part of their decision-making,” she says. “I think it will also move into being part of academies and maybe grassroots football.
“It should be something that really makes it more fun to play football.”
Page updated
Google Sites
Report abuse