AI Revolution in Soccer: Finding Competitive Edges

In soccer’s AI revolution, the machines don’t replace people. They chase the tiny edges everyone is desperate to find.

Clubs are rich, the margins are thin, and anything that hints at an advantage gets a hearing. Even if that “anything” is a chatbot.

From Arsenal blog to global scouting tool

Eyal Bracha didn’t enter the game through a boardroom door. He came in through a blog.

A devoted Arsenal fan, he started out writing long, detailed posts about the Gunners from home, mixing the eye test with early data tools to flag players big clubs should sign. The work caught on. Scouts started reading. His day job in tech got heavier, so he built an AI model to spit out the skeletons of his posts, then layered his own analysis on top.

That’s when things got interesting.

“I started to get inbox requests from professional scouts and at clubs asking me, ‘How do I know about that on a player?’” Bracha recalled. “I was like, ‘I don't know any of that about the player. Like, it's just ChatGPT.’”

If that level of output was impressing professionals, he wondered, what were they actually using?

The answer was messy. Clubs had numbers – mountains of them – but no shared language. Wyscout helped trigger the data boom in the early 2010s, then rivals piled in. Now, there are stats everywhere and clarity almost nowhere.

“In the past 10 years, this industry has moved from complete scarcity to data overload,” Bracha said. “There are so many different data providers.”

So he built Marquee.

The company, now working with clubs around the world, doesn’t drown teams in more spreadsheets. It tries to kill them. Marquee pulls data from scattered platforms, automates the grunt work and delivers a streamlined, club-specific view.

“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,” Bracha said. “In a sense, Marquee is an analytical department for this that works for the club.”

This is not Football Manager in a suit. Clubs pay Marquee to generate tailored player profiles: potential signings filtered not only by talent, but by tactical fit and club needs. Recruitment staff can ignore the suggestions if they want, but the tool is already embedded. A handful of Premier League teams use it. Barcelona and Chicago Fire have publicly backed it.

Whether Marquee is actually finding the next superstar is still an open question. But it’s part of the modern transfer ecosystem now, whether traditionalists like it or not.

When the machine spots fatigue before the player does

The AI story isn’t just about who clubs buy. It’s also about who they keep on the pitch.

Take FC Cincinnati’s MLS clash with Nashville SC last year. Center back Matt Miazga began to fade. Five minutes before he signaled that he needed to come off, the club’s system had already flagged “an irregular movement pattern.”

The data wasn’t live, so no one rushed to pull him because of a red light on a screen. The tech didn’t “save” him. But the machine saw something wrong.

The harder question came after the injury: when would he really be ready to return?

That’s where Springbok Analytics steps in. Their pitch to clubs is simple: send us your most complicated injury. Most of the time, that means hamstrings.

The numbers are brutal. A 2020 NIH study found that hamstrings account for 12 percent of all professional soccer injuries, with re-injury rates ranging anywhere from four to 68 percent. Clubs have thrown every test and gadget at the problem. The trend hasn’t improved.

“We’ve got all the new technology that exists every which way, all the new ways of testing people… how much force can you produce? What does running look like? Hamstring injuries have not gone down. They've gone up,” said Matt Brown, Analytics Director at Springbok.

He thinks part of the problem is the way the industry handles data. The injury itself is obvious. Quantifying what’s happening inside the muscle – strength, balance, atrophy – is not.

“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 said.

Springbok’s technology was born at the University of Virginia, where researchers used hyper-specific MRI analysis to help children with cerebral palsy. They built 3D graphics to guide surgeons on tendon lengthening. Once that started working, the company pivoted towards elite sport. The NBA signed on in 2023. MLS selected Springbok for its Innovation Lab this year.

Traditional MRIs, as Brown puts it, are “thousands and thousands of slices of [two-dimensional gray images].” Doctors have to mentally stack those slices into a 3D picture, then do their own painstaking calculations.

Springbok uses AI to do that heavy lifting.

“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. We process through them, create the muscle boundaries, and we can give a very finalized, beautiful 3D digital twin,” Brown said.

They don’t rehab the player. They don’t promise to prevent injuries. What they offer is speed and precision. Data that once took a week to turn around can now be ready in hours.

“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. But you're trained in this. You've done 10 years of this. You have your own thesis.”

The decisions stay with the doctors and physios. The machines just sharpen the picture.

Four photos, 10 seconds, and a glimpse of the future

At the other end of the pipeline, the Philadelphia Union academy staff wrestle with a different set of questions every day. How much can a teenager handle? Is he physically ready for a jump in level? Where’s the line between protecting a body and pushing a talent?

Players like Cavan Sullivan force those questions into focus. MLS clubs already run battery after battery of tests on strength, size and projected height. It’s slow. It’s manual. It’s guesswork dressed up as science.

Fit:Match wants to strip the process back to a phone and a few seconds.

Here’s how it works. A coach or parent takes four photos of a player from different angles. The software uses those images to calculate height, body mass, wingspan and a long list of other measurements. Then it projects growth, maturation and a rough picture of what full physical development might look like.

The founder, Haniff Brown, half-jokes that it’s “ChatGPT for soccer.” The comparison is about speed. A process that usually eats up time and staff resources is compressed into less than 30 seconds.

Brown didn’t start in sport. He started in fashion, building smartphone body scans to help customers buy clothes that actually fit.

“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 companies noticed. Then, in 2024, an unnamed European club asked Fit:Match to scan its academy. Brown saw an opening.

“I was very clear from the start that it had to take no more than 15 seconds,” he said. Coaches don’t want to stand around with clipboards. “They want the kids going back, doing their drills. The longer and more complicated the assessment is, the less likely they are to use it.”

The club bought in. Others followed. One major problem 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 wipes that out. Four photos, 30 seconds, one standardized profile. The tool now serves both clubs and families.

“When parents register their children to go into an academy, they can actually upload their photos. It generates their digital twin, and then on the back end, we tell MLS all these stats on that player,” Brown said.

That information feeds into one of the sport’s oldest biases: size. Youth soccer still leans toward early developers. Bigger, stronger 14-year-olds get picked. Smaller, late bloomers often disappear.

“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 might be. It also opens a door to awkward questions.

Ethics, jobs and the “build or buy” dilemma

Projecting a teenager’s future with a machine is not a neutral act. Nor is outsourcing huge chunks of scouting and analysis to an external platform.

Brown’s first task with Fit:Match wasn’t technical. It was emotional. “The first step was getting people comfortable,” he said.

Bracha learned the same lesson with Marquee. The platform can’t just drop into a club and start dictating decisions.

“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.”

Lurking behind the enthusiasm is a blunt reality: every new tool threatens someone’s job description. Bracha doesn’t dance around that.

“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 one of 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.”

But buying into AI doesn’t guarantee success.

Wolfsburg were among Europe’s early adopters. The club trumpeted that AI tools were saving €1 million per year on admin and injury prevention. On the pitch, though, results sagged. Performances dipped, and the club took heat for talking up its tech while the team struggled.

They’ve doubled down anyway. Sevilla now use IBM WatsonX to manage their data. The arms race isn’t slowing.

When ChatGPT picks your back line

Not every coach leans on AI in the same way. Some just poke at it.

Fraser – one of the many staffers experimenting in the background – admitted he played around with ChatGPT to explore matchup ideas and formations. Others have gone much further.

Seattle Reign head coach Laura Harvey made headlines in October 2025 when she revealed that she had asked ChatGPT directly: “What formation should you play to beat NWSL teams?”

For two of the league’s then-14 sides, the answer came back clear: play a back five.

Harvey didn’t blindly obey. She took the idea to her staff, weighed it up, and then the Reign switched to a system with five defenders. They finished fifth, climbing eight places from the previous season.

Did ChatGPT mastermind the turnaround? Of course not. But it did plant a seed that grew into a tactical shift on the field. For AI believers, that’s a tangible win.

There are plenty of dead ends too – models ignored, projections binned, ideas that never make it past the meeting room. Maybe that’s the point. AI is just another tool, another voice in a sport full of them.

And in a game this tight, with so much money and so little patience, the ethical debates rarely slow anyone down.

“We’re all looking for any advantage we can get,” Fraser said.

The question now is simple: when the next edge appears on a screen, who in soccer will dare to ignore it?