Before the ball was kicked, the Opta supercomputer had already played the tournament 25,000 times. Her verdict: Spain was the most likely winner, winning 16.1 percent of the simulations, closely followed by semi-finalists France, England and Argentina, each winning more than 10 percent.
Prediction quickly became much more than just a percentage on a page. It appeared on television, influenced betting markets, dominated social media discussions, and gave millions of fans a new way to follow the tournament. What started as a predictive experience has become part of how the World Cup is experienced in real time.
How the model works
As Jonathan Whitmore, Director of Analytics at Stats Performance, explains, the model combines Opta’s team rating with betting market odds. Team ratings are based on the Elo system, the same family of models used by FIFA. Elo weighs not only gains and losses, but the risks behind them. “Each individual team has points, and if you beat a team with a better score, you have the potential to earn more points and boost your score, whereas if you lose to a weaker team, they effectively get those points back, so it adapts over time,” Wetmore explains.
Germany’s shock defeat on penalties to Paraguay in the round of 32 shows how the system is adapting. The upset not only costs Germany a place in the draw, it effectively transfers rating points to Paraguay, reshaping both teams’ odds in each subsequent simulation.
However, ratings alone cannot capture everything that constitutes a match, so the model relies on a second data source to fill this gap: betting markets. “We indirectly take into account information such as injuries and team selection from the betting odds, so we are able to more accurately predict upcoming matches that will be played over the next few weeks,” Whitmore says.
Before the tournament, the model ran 25,000 simulations, far more than the 10,000 typically used in competitions such as the English Premier League due to the smaller number of total World Cup matches. This measure has paid off. In the semi-final stage, Spain, France, England and Argentina, the top four teams in the pre-tournament model, were also the final four teams in the tournament.
The value of artificial intelligence predictions
Prediction has evolved from a pre-game novelty to one of sports’ most valuable products. What was once a preview of the tournament is now a live stream of live broadcasts that enhance betting experiences and keep fans engaged from the opening whistle to the end. Building on the reliable Opta data that underpins modern football, the supercomputer has become one of the most trusted reference points in the sport.
The form is updated continuously. “For every goal, every red card, every final whistle and every penalty kick, we get an updated simulation showing who is most likely to win the tournament,” explains Whitmore.
Before the semi-finals, for example, France had overtaken Spain as favorites for the tournament, winning 34% of the model’s simulations. This constant recalculation is what makes modern forecasting so valuable. The tournament becomes a living story, where every moment is reflected in ever-evolving expectations.
This reflects a broader shift across sports media. As data evolves, it also becomes part of storytelling. Each goal changes the probability of lifting the cup. Every red card reshapes a team’s path to the final. Every result elsewhere recalculates the chances of qualifying. Prediction models deepen the drama by giving each key moment additional context, revealing how the match – and the tournament – will develop with each new development.
Watch any major football broadcast today, and you’ll find these ideas everywhere. The odds of winning lie next to the score line. Momentum graphics ebb and flow with the game. Qualification scenarios are updated instantly. These visual elements no longer seem new because they have become part of how football is watched and understood.
This represents a fundamental change in fan behavior. A decade ago, expected goals were a specialized metric discussed by analysts. Today, it’s part of everyday football conversation. Prediction models follow a similar path, moving from specialized analytics to the common language of sports.
For broadcasters, this context creates ongoing storytelling opportunities. Each potential update creates another talking point, another graphic, another social clip, another reason for viewers to stay engaged. Together, they turn a football match into an evolving story, with live prediction models updated throughout play.
BBC Sport showed this during Scotland’s decisive match in Group C. Using Opta’s live prediction data, viewers can watch Scotland’s chances of reaching the last 32 change throughout the match. The model predicted Scotland would qualify if they lost by no more than two goals, raising the stakes with each attack. Ultimately, Brazil’s goal erased that margin, ending Scotland’s World Cup run in real time.
That’s why fans appreciate the prediction. The appeal is not the ratio itself but the context it provides. Every goal, save or red card instantly transforms the story of the tournament, giving fans another reason to celebrate, debate or fear. with 93% of Generation Z By using a second screen while watching sports, live predictions naturally extend the experience beyond television, encouraging audiences to follow the story across multiple platforms.
The same data can also enhance personalized experiences. The casual fan may simply want to know who is most likely to win the tournament, while the loyal fan will want to understand his or her club or country’s changing path to the final. A reliable predictive model can support broadcast graphics, editorial coverage, fan experiences and betting products simultaneously.
In this way, predictive models have become the connective tissue between live sports data and audience understanding. As the volume of information increases, from historical performance to player tracking to real-time match events, the challenge is to understand what the data means in the moment. Predictive models provide that missing layer of interpretation, turning raw inputs into narratives, recommendations, and decisions across broadcasts, personal fan experiences, betting platforms, notifications, and emerging AI assistants. As mathematical data becomes more abundant and complex, prediction models provide the context that turns information into understanding. The companies that control this explanatory layer will shape how audiences experience live sports.
Trust as the ultimate competitive advantage
For sportsbooks, broadcasters and media companies, the business value extends even further. Prediction models help show how a match will develop before and during play, giving broadcasts, betting products and digital experiences a shared layer of trusted context. Live odds, predicted lineups, and tournament predictions increasingly support products and services built around live sports. None of this works without trust.
Broadcasters won’t build their programs around forecasts they don’t believe. Sportsbooks will not incorporate unreliable models into customer experiences. Fans will not go back to expectations that always fail to reflect the game on the field.
That’s why accuracy carries so much weight. The wrong end result is quickly forgotten. Repeated misprediction across broadcast graphics, betting products, editorial content and notifications becomes a credibility issue that multiplies across every platform you rely on. As prediction becomes more valuable, trust becomes more important.
Perhaps the clearest evidence of this confidence came not from a broadcaster or a bookmaker, but from the man who runs world football itself. When asked about Spain’s pre-tournament title favorites rating by supercomputer Opta, FIFA president Gianni Infantino simply smiled and replied: “Well, if Opta says so.”
It was a light remark, but it contained something important. Opta’s supercomputer and prediction models are reliable not because they use artificial intelligence, but because they are built on the data that millions of broadcasters, sportsbooks, clubs and fans already rely on to understand the game.
As AI continues to evolve, prediction models will become more complex. However, its greatest value will remain the same: helping millions of people understand, in real time, how each moment changes the story unfolding before them.
