As EURO 2021 kicks off, Big Data and AI are making an impact in global football

In 2019, Liverpool FC dominated the Champions League, the most prestigious cup in club football. Almost everything seemed to go their way: a clever and capable coach, a talented and driven team, and a few tricks that kicked in at just the right time. At first glance, it seemed that luck was shining on the team — but this was not luck. Liverpool was leveraging the power of big data and artificial intelligence.

A hallmark of Liverpool’s 2019 season: the compact block formed by the players, forcing opposing teams to go around to the sides, where they had fewer chances of scoring goals. Credits: Liverpool FC.

Sports and science

A look through Liverpool’s research team shows you they take data very seriously. The director of the club’s research division, Ian Graham, holds a PhD in theoretical physics, and he focuses on finding trends that might escape the naked eye. By gathering large sets of data and crunching the numbers, he can find sophisticated patterns that can help the team prepare against opponents or find a winning strategy.

“What we’ve built is a platform where the analysts can either look at the opposition analysis or post-match analysis from our point of view, so we’ve got expected goals models and expected possession value models that are linked to video to say: ‘This is what we thought was a dangerous situation.’”

“Jürgen [Klopp, Liverpool’s manager] is very open and receptive to our area,” Graham notes.

Graham is not alone in this quest. Tim Waskett, an astrophysicist, and Will Spearman, who has a doctorate in philosophy, are two of his colleagues. Both have spoken about pitch control — which team controls what part of the pitch. They think of passing and scoring in terms of geometry and odds: What areas are the most likely to be controlled by our team, instead of theirs? What type of pass is most likely to lead to a goal? They generate plots such as the one below to help the player know where to pass. In the image, blue spots are controlled by “us”, while red plots belong to “them”.

The player controlling the ball (in the yellow circle) is advised to pass to one of the blue areas. Image credits: Liverpool FC.

Strategizing against other teams is just one of the ways AI and big data are used in football. In a recently published paper, Liverpool FC teamed up with researchers from DeepMind (the AI company behind the likes of AlphaZero and AlphaChess) to test how “AI-enabled system can assist humans in making complex, real-time decisions in a multiagent environment with dozens of dynamic, interacting individuals.”

The motivation is easy to understand: we’ve never had access to this much information about players and teams — you can track players’ movements, where shots go, individual behavior, and many more. You can use the big data directly, or feed it into models, and there are ways to use this at every single level of the game: from individual training to finding tactical ideas in tough situations.

Predictive models

The paper and an accompanying blog post from DeepMind highlight three areas where AI and big data can make a difference: computer vision, statistical learning, and game theory.

“While these fields are individually useful for football analytics, their benefits become especially tangible when combined: players need to take sequential decision-making in the presence of other players (cooperative and adversarial) and as such game theory, a theory of interactive decision making, becomes highly relevant. Moreover, tactical solutions to particular in-game situations can be learnt based on in-game and specific player representations, which makes statistical learning a highly relevant area. Finally, players can be tracked and game scenarios can be recognised automatically from widely-available image and video inputs,” the DeepMind team explains.

An example illustration of an envisioned automated video-assistant coach interface, where attacking and defending players are detected, identified (in terms of player names), tracked, and subsequently passed into a predictive trajectory model. Image credits: DeepMind.

For instance, player behaviors on the pitch (both from “our” team and “theirs”) could be gathered from video recordings, which are already widely available. Game scenarios such as attacks, set pieces, or even entire games, could then be simulated and recognized automatically, with the algorithms spotting patterns that the players themselves may not be aware of. These models could also predict the implications of a tactical change or a substitution, estimating the opposition’s response to the change.

Managers could also use predictive models to simulate games between their team and others and try out various starting lineups or strategies, seeing the scenarios where the model estimates you’d fare best. Of course, this is bound to be an imperfect simulation, but it may offer important insights nonetheless. After all, the goal of AI isn’t to replace coaches or managers, but rather to help squads optimize their training and game preparation.

Example of predictive modelling using football tracking data. Here, the ground truth data for the ball, attackers, and defenders is visualised in addition to defender predictions made by a sequential-predictive trajectory model. Image credits: DeepMind.

Who benefits the most from this?

Football has changed a lot in recent years, and much of that change has based on analytics. Big data is supercharging that trend, and the application of AI techniques has the potential to revolutionize the game on many axes (not just for players and coaches, but also for drafters and broadcaster). A part of this still feels ethereal — almost close enough to touch, but not fully tangible yet.

But we’re already starting to see some impacts. Liverpool FC is a pioneer, but not an exception. More and more teams are investing serious resources into this type of project, because the potential benefits (even from imperfect models) are so great. Football is, of course, a multi-billion dollar industry, and every bit of useful information can make a big difference.

This all begs the question: will all these techniques help football become democratic, by democratizing the sport (for instance, rather than relying on big teams of scouting experts, team can use computer techniques to analyze players), or will only the rich teams be able to afford this, and will they grow even more as a result? The jury is still out, and the change won’t happen overnight.

There are still major research challenges. DeepMind mentions that predictive football models “require new developments and progress”, and football is (and will remain) an unpredictable sport. A 2021 study found that almost half (46%) of goals have some form of random influence in them. AI can help offer a competitive long-term edge, but it’s unlikely to be able to incorporate the complexity and randomness coming. For now, at least, football is still very safe from being predictable.

Avatar photo

Posted by

Andrei is a science communicator and a PhD candidate in geophysics. He is the co-founder of ZME Science, where he published over 2,000 articles. Andrei tries to blend two things he loves (science and good stories) to make the world a better place -- one article at a time.


  1. Yes, Artificial Intelligence applied to game situations, situations where reward / punishment for correct / wrong behavior is enough to keep getting better and better, can produce superhuman results as AI techniques like reinforcement learning, applied to games, can be used to simulate the same game and thousands of game variants in a few CPU hours while real people could only play all the variations in years of game practice. This applies not only to football, but also to board games such as Go, in which the Deep Mind programs Alpha Go and later Alpha Zero played / simulated billions of Go games and discovered moves that were not yet known to mankind but turned out to be have proven to be groundbreaking. The same could happen in football, where the AI ​​has the chance to find winning strategies through pure simulation power.

    As mentioned in the article above, soccer is full of random events and this can become a problem for an AI system when the nature of the randomness is undetectable and cannot be modeled by the computer. On the other hand, randomness is also known to be a chance to mix up the game if you play the ball seemingly randomly, because it depends on the fast and correct reactions of the players and some players can use the randomness to their own advantage. With random ways of playing you can reveal your opponent’s weaknesses.

  2. Who benefits the most from this?
    Better live gaming through the use of artificial intelligence will not only help football and other sports, but also all human team activities that can be gameified, that can be viewed as a game with a quantitative goal.

    There are many important activities that can be viewed as games.

    For example, rescuing people in a disaster area (e.g. the situation immediately after a major earthquake) can be viewed as a game in which you get more points if you rescue more people in a shorter time. Artificial intelligence could use all past disasters as a training set and then develop an efficient strategy to improve recovery success.

    There are many other examples in which gameification makes it possible to use artificial intelligence as an aid, as an organizational tool.

    Even the improvement / optimization of a battery through certain changes in the cell chemistry could probably be modeled as a game to be optimized and the artificial intelligence used would try to get as high a score as possible in this game.

  3. Quote:

    Football is (and will remain) an unpredictable sport. A study from 2021 found that almost half (46%) of the goals are randomly influenced.

    Yes, but does this not apply to most human endeavors? – even the choice of your spouse can be attributed to a (quote) “somehow random influence” A certain degree of randomness corresponds, for example, to noise in a perception task. Artificial intelligence has no problems with that. Football will certainly always be a game played by people and will have a human touch. The same goes for chess or go – even when future players of these games use game engines to master these games.

  4. Will superhuman replace humans?
    Doomsters and Worryiers often assume that artificial intelligence will fight humanity to overtake the world. But why should Artificial Intelligence do that? AI programs like virtual soccer coaches or self-driving cars (obviously, apparently?) Have the opposite goal: They want to help people by being as good or even better than humans: they want to be better soccer players than human players, better drivers than human drivers. And people even ask for it. A colleague of mine said: “Robo-taxis should only be allowed if they cause zero accidents. Not ten times fewer accidents, but zero accidents. ”This attitude and expectation towards artificial beings that the AI ​​that takes care of human affairs should be much more perfect than humans is widespread.

    Most people do not know, however, that the demand for superhuman performance by artificial creatures is the real threat to us humans – and not the (non-existent) will of artificial beings to eliminate us.

    Think about it.

    If autonomous cars don’t make mistakes, people will be banned from driving, or if not banned, you will get 10 years in prison for injuring someone driving instead of letting the car drive them.

    If robot lawyers and judges are always impartial and know the law better than anyone, then it is only a matter of time before human lawyers are deemed obsolete.

    If robot lovers are better than human lovers in every way, they are preferred.

    If robots are better people, then the last human on this planet will have a robot spouse and robot child.

  5. Data is power and money buys people and data

    will all these techniques help football become democratic, by democratizing the sport (for instance, rather than relying on big teams of scouting experts, team can use computer techniques to analyze players), or will only the rich teams be able to afford this, and will they grow even more as a result?

    My prediction: Football AI analytics will even appear in computer games because software is cheap (cheap to copy). The really expensive and exclusive things are people and data, both of which you have to buy. Think about it:
    – the best soccer AI analysis won’t help you if you don’t have the right physically competent soccer players (soccer robots in the future?)
    – AI software from Amazon and Google (e.g. recommendation software) or Waymo (digital city maps) only makes sense for Amazon and Google because both companies have digital data riches: Google and Amazon have personal data of billions of customers and Google has images and maps of every corner of the world. Only those who have access to this data can earn money with today’s AI algorithms
    – More data on all football players worldwide (game profile, digital archive of all his games) enable more informed decisions as to whether this football player is worth his money and fits into the football team. Better informed decisions will give richer football teams even more power and dominance than they do today because those rich teams’ money becomes more effective: they buy players who are really worth their money.

  6. Your post discusses the potential of investing in real estate properties or rental properties as a way to generate passive income and build long-term wealth. It’s a tangible asset that can yield significant returns. click here for additional details.

Leave a Reply

E-Mail-Benachrichtigung bei weiteren Kommentaren.
-- Auch möglich: Abo ohne Kommentar. +