The Impact of AI on Football Scouting and Player Management
The future of football isn’t arriving in a lab or a boardroom. It’s sneaking in through scouting inboxes, academy WhatsApp groups and medical imaging suites – all under the banner of AI.
Some clubs are already hooked. Others are still suspicious. But nobody can ignore it.
From Arsenal blog to global data plug-in
Before he became a tech supplier to elite clubs, Bracha was just another obsessive Arsenal fan with a blog and a day job in tech.
He watched games, crunched numbers, mixed the “eye test” with whatever tools he could find and started flagging players he thought big clubs should sign. The work got him a following. Then life got busier.
So he built himself a shortcut.
He trained an AI model to spit out the skeletons of his blog posts. He still did the thinking, but the machine handled the heavy lifting. Somewhere along the way, the lines blurred. He started using large language models to help identify players, too.
The response stunned him.
“I started to get inbox requests from professional scouts and at clubs asking me, ‘How do I know about that on a player?’” he recalled. “I was like, ‘I don't know any of that about the player. Like, it's just ChatGPT.’”
If that impressed professionals, he wondered, what were they using?
The answer: a mess of numbers, platforms and half-compatible systems.
Drowning in data, starving for clarity
Football’s data revolution arrived fast and loud. Companies like Wyscout helped drag scouting out of the VHS era in the early 2010s. Rivals piled in. Tracking data, event data, physical data – every club could access mountains of information.
Too much, in fact.
“In the past 10 years, this industry has moved from complete scarcity to data overload,” Bracha said. “There are so many different data providers.”
Clubs had numbers. They didn’t always have answers.
That gap is where Bracha’s company, Marquee, now lives. It doesn’t sell a shiny app for fans or a game-like interface for directors of football. It sells time.
“If we automate a lot of these, so to speak, glorified spreadsheet processes, and the different platforms that are scattered and cannot be consolidated into one place. We do it for them,” he explained. “So, in a sense, Marquee is an analytical department for this that works for the club.”
The pitch is simple: Marquee ingests data from multiple providers, cleans it up, then spits out tailored recruitment profiles. Not wonderkids from Football Manager. Not fantasy signings from EAFC Career Mode. Actual targets, costed and filtered for tactical fit.
Clubs can ignore the recommendations if they want. They often do. But enough have listened that Marquee now works with teams across the world, including several in the Premier League, and has been publicly backed by Barcelona and MLS side Chicago Fire.
Whether that leads to the next hidden gem is another debate. For now, it means AI is embedded in how clubs think about players.
When the machine knows your defender is done
The technology isn’t just pointing at transfer lists. It’s creeping into the medical room, too.
In one MLS game last year, FC Cincinnati faced Nashville SC. Late on, their system flagged something unusual: center-back Matt Miazga’s movement pattern had shifted. The alert came five minutes before he signalled that he needed to come off.
The club didn’t use that data to force him to play through pain. The information wasn’t even live. But the machine had seen something the human eye didn’t fully catch in time.
Spotting the problem is one thing. Predicting when a player can truly come back is another. That’s where Springbok Analytics believes it can change the game.
Their request to clients is blunt: “Send us your most complicated injury.”
Most of the time, that means hamstrings – the injury football still hasn’t solved. A 2020 NIH study found hamstrings account for 12 percent of all professional soccer injuries, with re-injury rates swinging wildly between four and 68 percent.
Clubs know the pattern. Hamstrings often go late in halves, when fatigue bites. They know rehab protocols, too. But the global injury numbers haven’t fallen. As Matt Brown, Springbok’s Analytics Director, put it: “Hamstring injuries have not gone down. They've gone up.”
He thinks data – the right kind of data – is missing.
Turning gray scans into 3D “digital twins”
Springbok’s story starts far from football. At the University of Virginia, researchers developed hyper-detailed MRI techniques to help treat children with cerebral palsy. The scans produced 3D graphics so surgeons could precisely calculate tendon lengthening procedures.
When that worked, the technology moved into sport. The NBA signed up in 2023. MLS picked Springbok for its Innovation Lab this year.
Traditional MRIs are, as Brown describes them, “thousands and thousands of slices of [two-dimensional gray images].” Doctors stack them, interpret them and slowly build a 3D picture in their heads. It takes time and experience.
Springbok uses AI to speed that up.
“We can now pre-process those images using AI… we can get all the crazy MRI images and the 3D space and time and all the stuff that exists there,” Brown said. “We process through them, create the muscle boundaries, and we can give a very finalized, beautiful 3D digital twin.”
The point isn’t to magically heal anyone. Springbok doesn’t treat injuries or promise prevention. It tracks them. Precisely.
“You want to scan a player at the time of injury, two months later, six months later, to track atrophy and see if you're getting the stimulus and the changes that you're going after with muscle,” Brown explained.
Where a club might wait a week for that level of analysis, Springbok can deliver it in hours. The doctors still make the decisions. They just get sharper measurements, faster.
“We are the support system in that we can make imaging from an MRI way more impactful and actionable,” Brown said. “We are not the ones that actually actualize it for you. We are providing you the measurements.”
Ten seconds to see a teenager’s future
At the other end of the pipeline, the questions are different but no less complicated.
Every day at Philadelphia Union’s academy, staff wrestle with the same dilemmas as their peers around the world. How much can a 15-year-old play? What level is a 13-year-old really ready for? Is a prodigy like Cavan Sullivan physically prepared for the demands of senior football?
Clubs test height, strength, predicted growth, peak performance. It’s laborious and often inconsistent.
Fit:Match wants to compress that entire process into a few taps of a phone.
All it needs is four photos, taken from different angles. From there, the system calculates height, body mass, wingspan and a long list of other measurements. Then it projects forward: likely adult height, growth stage, a basic outline of what full physical maturity might look like.
Founder Haniff Brown calls it “ChatGPT for soccer” with a half-smile. The comparison isn’t totally off. What used to be a slow, manual assessment becomes an automated report, delivered in under 30 seconds.
Brown didn’t start in sport. He came from fashion, where he used instantaneous body scans to stop customers buying four shirts and sending three back.
“How can we allow [a user] to upload a body profile of himself so that he doesn't have to buy four shirts and return the three that don't fit? You'll just buy one and boom,” he said.
Hospitals and healthcare providers noticed. Then, in 2024, a European club asked him to scan its academy. Brown saw a bigger opportunity – but knew he had to respect football’s rhythm.
“I was very clear from the start that it had to take no more than 15 seconds,” he said. “Coaches don't like assessments that take too long. They want the kids going back, doing their drills.”
The shorter the test, the higher the chance it actually gets used.
Standardising what coaches can’t agree on
The first club was convinced. Others followed. One issue kept popping up: human inconsistency.
“What we saw was one coach would, for the same player, measure and get one result, and from the same team, another coach would measure that same player and come up with a different result,” Brown said.
Fit:Match strips that out. Same four photos. Same process. Same output.
Parents can now upload images when registering their children for academies. The platform creates a “digital twin” and feeds a detailed physical profile back to MLS in the background.
That helps clubs decide which age groups players should join and how to structure their development. It also tackles one of youth football’s oldest biases: size.
“A player who is a 14-year-old but an early developer is far different from a player who's 14 and a late developer,” Brown said. “Now MLS can scientifically tell that, and then make better pathways for those late developers so that they don't drop out of the ecosystem.”
It sounds transformative. It also opens a door into tricky ethical territory.
The uneasy questions: jobs, judgment and teenagers
Predicting a teenager’s future has always been dangerous. Doing it with machines doesn’t make it any cleaner.
“The first step was getting people comfortable,” Brown admitted. Clubs had to trust that the technology wasn’t replacing them, just sharpening their view.
Marquee faced the same challenge. Bracha realised early that he couldn’t simply parachute in with a magic algorithm and tell clubs what to do.
“It's more about them, to be fair, to kind of feel comfortable with everything that we do together,” he said. “And then once we create some successful stories together, we will definitely publish it.”
There’s also the blunt economic question: if a club buys an AI platform, does it still hire as many analysts?
Bracha doesn’t dance around it.
“From an ROI perspective, it will always be faster, quicker, righter to go to us because we've already built something, and we're investing a lot to improve it. It's your only expense,” he said. Salaries are among a club’s biggest costs. “So do they want to hire more to build such a thing or just buy externally? It's like the AI’s most common question nowadays: build or buy? In this case, I think buy.”
That logic appeals to owners and executives. It doesn’t guarantee anything on the pitch.
Wolfsburg’s warning – and Sevilla’s bet
Wolfsburg were one of Europe’s early AI flagbearers. They claimed savings of €1 million per year by automating administrative work and aiding injury prevention. The PR blitz was loud.
The results weren’t.
As performances dipped, the club took heat for trumpeting its tech while the team struggled. The backlash didn’t push them away from AI. If anything, they leaned in harder.
Sevilla, meanwhile, turned to IBM WatsonX to help manage their data. The tools differ, the message doesn’t: elite clubs are betting that smarter information handling will eventually translate to smarter decisions.
Sometimes, the experiments are quieter – and more personal.
When ChatGPT picks your back five
Seattle Reign head coach Laura Harvey caused a stir in October 2025 when she revealed on the Soccerish podcast that she’d asked ChatGPT a very specific question: “What formation should you play to beat NWSL teams?”
For two of the league’s then-14 sides, the AI’s answer was clear: play a back five.
Harvey didn’t just copy-paste the suggestion. She thought about it, took it to her staff and adapted it. The Reign eventually rolled out a system with five defenders.
They finished fifth – eight places higher than the previous year.
Did ChatGPT mastermind their revival? Of course not. But it planted a seed that grew into a real tactical shift. For AI believers, that’s enough. The tool sparked an idea that ended up on the pitch.
Plenty of other experiments have fizzled. Some data gets ignored. Some models miss the mark. That might be the point. AI isn’t a magic wand. It’s another lens.
And in a sport decided by inches, that lens is hard to turn down.
“We’re all looking for any advantage we can get,” Fraser said.
In the arms race of modern football, that mindset is all the invitation AI needs.
