AI points to Brazil as favorite in Qatar 2022

Brazilwith 15% chance to win, will be the favorite to win World Cup 2022 in Qatar, according to the calculations of a group of scientists using machine learning.

Also, teams from Argentina (11.2%) have “many chances for the title”; the Netherlands (9.7%); Germany (9.2%) and France (9.1%), followed by Spain with 7.5%, according to a study by the universities of Innsbruck (Austria); Ghent (Belgium); Luxembourg and technical universities of Dortmund and Munich (Germany).

How was this result determined?

The forecast combines several statistical models of teams’ “playing strength” with information about the structure of teams (eg market value or number of players in the Champions League) as well as the country’s socio-economic factors. origin (population or gross domestic product).

“This time, World it is overshadowed by many ethical and sporting issues that we cannot ignore. However, for scientific reasons, we decided to use our machine learning approach, which we have successfully applied in previous tournaments, to make probabilistic predictions,” said one of the authors, Achim Zeileis, quoted by the University of Innsbruck.

With the values ​​predicted by the scientists’ model, the entire World Cup was simulated 100,000 times, match after match, after the draw of the tournament and all the rules of the tournament. FIFAwhich returns the odds with which teams will advance to the various rounds of the tournament and ultimately win the championship.

The authors claim that their study provides “probabilities, not certainties. A 15 percent chance of winning also means an 85 percent chance of losing.”

Qatar 2022: more than interesting

FIFA World Cup in Qatar it is especially scientifically interesting due to the unusual rendezvous that takes place in the winter due to the high temperatures in the summer.

During the winter months, all major football leagues in Europe and South America are forced to interrupt their regular match schedules to adjust to the tournament, giving national teams less time to prepare and players less time to recover before and after the tournament.

In addition, extreme weather increases the risk of injury, Zeilis explained. Thus, having a team with many players in international leagues such as the Champions League, Europa League or the European Conference League “may turn out to be more of a disadvantage than an advantage this year.”

“All these factors make it difficult to predict how a tournament will play out, as variables that were very significant in previous World Championships may not have worked properly or worked differently,” said Andreas Groll, another contributor to the study published Reports and materials.

The scientists’ calculation is based on four sources of information: a statistical model of the “playing strength” of each team, based on all international matches over the past eight years, and another model of the “playing strength” of the teams. by betting odds from 28 bookmakers

The third base is additional information about the teams, such as the market value and their countries of origin, such as population, and the fourth is an automatic learning model that combines various sources and optimizes them step by step. , step. EFE

We recommend you METADATA, an RPP technology podcast. News, analytics, reviews, recommendations and everything you need to know about the tech world.