Supercomputer Predicts Brazil Will Win The World Cup After Defeating Argentina In The Finals

A World Cup supercomputer predicted that Brazil will win the World Cup after defeating Argentina in the finals.

Scientists reportedly used an AI (Artificial Intelligence) technique known as ‘random forests’ and simulated Qatar 2022 100,000 times match by match. Based on the algorithm obtained, the AI predicted that Brazil will win the World Cup after defeating Argentina in the finals. According to the algorithm, Netherlands and Germany will be defeated in the semi-finals and England will crash out of the World Cup in the quarter-final stage, WalesOnline reported.

“This time, the World Cup is overshadowed by many ethical and sportive problems we cannot ignore," Statistician Professor Achim Zeileis, of the University of Innsbruck in Austria, said.

“Nevertheless, for scientific reasons, we have decided to use our machine learning approach, which we have used successfully at previous tournaments, to make probabilistic forecasts.”

The AI model, which is based on adjusted bookmakers' odds, has been remarkably successful in the past. It successfully predicted the 2008 Euro final between Spain and Germany. It also correctly predicted Spain being crowned World and European champions in 2010 and 2012.

According to the AI predictions, Brazil is leading with a probability of winning of 15 percent, followed by Argentina (11 percent), the Netherlands (10 percent), Germany (nine percent) and France (nine percent), Spain (eight percent), England (seven percent) and Belgium (six percent).

Calculations were made based on a statistical model for the playing strength of each team across all the international matches that the team has played in the past eight years. Betting odds from 28 leading bookmakers, players’ market value, and their countries of origin were also taken into consideration.

“We fed the model with the current data for the past five World Cups, between 2002 and 2018, and compared it with the actual outcomes of all matches in the respective tournaments, " Co-author Professor Andreas Groll, of the Technical University of Dortmund in Germany, said.

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

"It is in the very nature of forecasts they can also be incorrect – otherwise football tournaments would be very boring. We provide probabilities, not certainties, and a probability of winning of 15 percent also implies a probability of 85 percent of not winning,” Professor Groll added.