Before the ball was kicked, Opta’s computer had played the tournament 25,000 times. His verdict: Spain is the likely winner, winning 16.1 percent of the ratings, followed closely by semi-finalists France, England and Argentina, each winning more than 10 percent.
The prediction quickly became more than a percent on the page. It appeared on television, influenced betting markets, dominated social media conversations and gave millions of fans a new way to follow the competition. What started as a prediction turned into a real-time World Cup.
How the model works
As Jonathan Whitmore, director of statistics at Stats Perform, explains, the model combines Opta’s group average and betting market volatility. Team ratings are built on the Elo system, the same family of models used by FIFA. Elo not only measures wins and losses but also the statistics behind them. “Each team has points, and if you beat a team with a better score, you have the ability to win more points and increase your score, and if you lose to a weaker team, they effectively win those points back to you, so it’s fixed over time,” explained Whitmore.
Germany’s shocking penalty shootout loss to Paraguay in the Round of 32 shows how the system is adapting. The upset not only cost Germany a spot in the draw, but it also transferred the equalizer to Paraguay, fixing both teams’ problems in all subsequent simulations.
Measurements alone, however, cannot capture everything that shapes the same, so the model relies on a second data source to fill that gap: betting markets. “We’re indirectly accounting for information like injuries, team selection and betting odds,” Whitmore said, “so we’re able to accurately predict those upcoming games coming up in the next few weeks.”
Before the tournament, the model used 25,000 simulations, more than 10,000 of which are usually used for competitions such as the Premier League due to the total number of World Cup matches. That scale paid off. In the semi-finals, Spain, France, England and Argentina, who were the top four teams in the tournament before the tournament, were also the last four players in the tournament.
The number of AI predictions
Prediction has evolved from a pre-match novelty to one of the most important sports products. What was once a tournament preview is now a live streaming service that empowers insight, enriches the betting experience and keeps fans engaged from the opening whistle to the final whistle. Built on Opta’s trusted data that supports modern football, the Supercomputer has become one of the most trusted sites in sports.
The model is continuously updated. “For every goal, every red card, full-time penalty, every penalty, we get an updated simulation that shows who is likely to win the tournament,” explained Whitmore.
Before the semi-finals, for example, France had overtaken Spain as the tournament favorites, winning 34 percent of the polls. That constant recalculation is what makes modern predictions so important. The tournament becomes a live narrative, all the time shown on the ever-changing weather forecast.
This reflects a broader shift in all sports media. As data becomes more complex, it has also become part of storytelling. Every goal changes the chances of lifting the trophy. Every red card rebuilds the team’s route to the final. All results elsewhere recalculate the probability of eligibility. Prediction models deepen the drama by giving each moment more context, revealing how the game—and the tournament—evolves with each new development.
Watch any major football broadcast today, and that detail is everywhere. The odds of winning stay close to the score line. Momentum graphics ebb and flow with the game. Eligibility conditions are updated immediately. These views no longer feel new because they have become part of the way football is viewed and understood.
That represents a significant change in fan behavior. Ten years ago, expected goals were a professional metric discussed by analysts. Today, it is part of the everyday football conversation. Prediction models follow a similar trajectory, moving from niche statistics to the shared language of sports.
For broadcasters, that context creates ongoing opportunities for storytelling. Every possible update creates another talking point, another image, another social clip and another reason for viewers to stay engaged. Together, they transform the game of football into a dynamic story, with live prediction models that are updated throughout the game.
BBC Sport showed this when Scotland played a Group C game. Using Opta’s live prediction data, viewers can watch Scotland’s chances of reaching the Round of 32 change during the game. The actor revealed that Scotland will advance if they lose by no more than two goals, increasing the number with each attack. Brazil’s goal finally lifted those restrictions, ending Scotland’s World Cup in real time.
That’s why fans value speculation. The appeal is not the percentage itself but the context it provides. Every goal, save, and red card creates an immediate change in the narrative of the tournament, giving fans another reason to celebrate, debate or fear. With 93 percent of Gen Z using a second screen while watching sports, live predictions naturally extend the experience beyond television, encouraging audiences to follow the story on multiple platforms.
The same data can also enable personalized experiences. A casual fan may want to know who is likely to win the tournament, while a dedicated fan wants to understand their club or country’s changing path to the final. A single reliable predictive model can support broadcast images, programming streams, fan experiences and betting products simultaneously.
In this way, predictive models become the connective tissue between live sports data and audience insights. As the volume of information grows, from historical performance to player tracking to real-time game events, the challenge is to make sense of what the data currently means. Predictive models provide the missing translation layer, turning raw input into stories, recommendations and decisions across streams, personalized fan experiences, betting platforms, notifications and emerging AI assistants. As sports data becomes more abundant and complex, predictive models provide the context that turns information into insight. Companies that control this defining layer will change the way audiences experience live sports.
Trust as the last competitive edge
For sportsbooks, broadcasters and media companies, the value of advertising expands even further. Predictive models help explain how a match unfolds before and during play, giving broadcasts, betting products and digital experiences a shared layer of reliable context. Live odds, line ups and tournament predictions are increasingly supported by products and services designed for live sports. None of this works without trust.
Broadcasters will not make programs based on predictions they do not believe. Sportsbooks will not include models that are not reliable in the customer experience. Fans will not go back to predictions that always fail to show the game on the field.
This is why accuracy is so important. The last bad score is quickly forgotten. Repeated mis-predictions across streams, betting products, editorial content and push notifications become a recurring credibility issue for every platform that relies on it. As predictability becomes more valuable, trust becomes even more important.
Perhaps the clearest expression of that trust came not from the broadcaster or the bookie, but from the man in charge of world football himself. Asked about Spain’s inclusion as pre-tournament favorites by the Opta Supercomputer, FIFA President Gianni Infantino simply smiled and replied, “Well, if Opta says so.”
They were simple words, but they carried something important. Opta Supercomputer models and predictions are trusted not because they use AI, but because they are built on data that millions of broadcasters, sportsbooks, clubs and fans already rely on to understand the game.
As AI continues to evolve, predictive models will become more sophisticated. Their greatest value, however, will remain the same: to help millions of people understand, in real time, how each moment changes the story unfolding in front of them.
