English football fans hope Harry Kane and co. can emulate the Lionesses and return from Qatar as a World Cup winner.

But according to a supercomputer, there will be no end to the 56 years of suffering the men’s team has endured since last winning a major competition.

Indeed, a series of statistical models point to Brazil being favorites to emerge victorious from the World Cup 2022.

If you like a bet, the supercomputer suggests that Brazil will face Argentina in the final on December 18 – but know that a similar prediction for the 2018 World Cup was wrong.

It also picked five-time winners Brazil to win, only for France to emerge victorious by beating Croatia in Moscow.

Predictions: English football fans are hoping the Three Lions can return from Qatar as World Cup winners. But according to a supercomputer, that won’t happen. This graph shows the probability of winning the competition, with favorites Brazil, Argentina and the Netherlands

Who can beat who? This graph shows the teams with a probability of fighting. The color scheme uses green versus purple to signal probabilities above and below 50%, respectively

A series of statistical models indicate that Brazil are the favorites to emerge as winners of the 2022 World Cup again

The predictions for the 2022 FIFA World Cup were made by an international team of researchers using a hybrid model that combines data from three advanced statistical models.

After being knocked out in the quarter-finals four years ago, the Brazilian national team are once again the heavy favorites, with a 15% probability of victory.

They are followed by Argentina, the Netherlands, Germany and titular France, according to a team of experts from the universities of Innsbruck, Ghent and Luxembourg and the technical universities of Dortmund and Munich.

But for Gareth Southgate’s men, the quarter-final is where models think they’ll crash.

They have just a 7.4 per cent chance of winning the World Cup in the same year the women’s team lifted the Euro 2022 trophy at Wembley in July.

The predictions combine several statistical models for the playing strengths of the teams with information on the structure of the team (such as the market value or the number of Champions League players) as well as socio-economic factors of the country of play. origin (population or gross domestic product).

“For scientific reasons, we decided to use our machine learning approach, which we have used successfully in previous tournaments, to make probabilistic predictions,” said Achim Zeileis, from the university’s statistics department. from Innsbruck.

With the predicted values ​​from the researchers’ model, the entire World Cup was simulated 100,000 game-by-game times.

This led to odds for all teams to qualify for the various rounds of the tournament and ultimately win the World Cup.

Of course, the tournament is far from predetermined, which is reflected in the relatively low probability of victory for the top teams.

Argentina has an 11.2% chance of winning, the Netherlands 9.7%, Germany 9.2% and France 9.1%.

“It is in the very nature of predictions that they can also be incorrect – otherwise football tournaments would be very boring.

“We provide probabilities, not certainties, and a 15% probability of winning also implies an 85% probability of not winning,” explained Andreas Groll.

This graph shows the probability of each team qualifying for the Round of 16, Quarter-Finals, Semi-Finals, Final and then winning the World Cup

For Gareth Southgate’s men, the quarter-final is where they will crash, according to statistical models. They have just a 7.4 per cent chance of winning the World Cup in the same year the women’s team lifted the Euro 2022 trophy at Wembley in July.

The 2022 World Cup is interesting for researchers from a scientific point of view because of the unusual date – the tournament had to be postponed to the winter months due to extremely high temperatures in Qatar in the summer.

“During the winter months, all the major football leagues in Europe and South America have to interrupt their regular fixture schedule to host the tournament,” said Achim Zeileis.

“It gives national teams less time to prepare and players less time to recover before and after the World Cup. Combined with the extreme weather conditions, this also increases the risk of injury.

Having a team with many players in international leagues – such as the Champions League, the Europa League, the Europa Conference League – could therefore prove to be more of a disadvantage this year than an advantage.

Mr Groll added: “All of these factors make it harder to predict how the tournament will play out, as variables that have proven to be very significant at previous World Cups may not work well or work differently.”

The researchers’ calculation is based on four sources of information.

Argentina, the Netherlands, France, Germany and Spain (pictured) will all be there or thereabouts

The first two are a statistical model of each team’s playing strength based on all international matches for the last eight years and another statistical model of the teams’ playing strength based on the betting odds of 28 international bookmakers.

Further information about the teams, for example market value, and their countries of origin, such as population size, are the third, while the fourth is a machine learning model that combines different sources and optimizes them step by step.

The researchers previously trained the model with historical data.

“We fed the model with current data from the last five World Cups, i.e. between 2002 and 2018, and compared it with actual results from all matches in the respective tournaments,” Mr. Groll.

“This way, the weighting of the different sources of information for the current tournament will ideally be very accurate.”