Researchers at the Technical University of Dortmund have developed machine-learning techniques that have the potential to exceed conventional statistical approaches.

The 2018 soccer World Cup commences in Russia this week, as one of the most widely viewed sporting events in history, exceeding the popularity of the Olympics.

In the growing interest of potential winners and predictions, companies use professional statisticians to analyze extensive databases of results in a way that quantifies the probability of different outcomes of any possible match.

Andreas Groll and colleagues at the Technical University of Dortmund in Germany use a combination of machine learning and conventional statistics, a method called a random-forest approach, to identify a different most likely winner.

The team co-simulated the entire tournament 100,000 times. “According to the most probable tournament course, instead of the Spanish the German team would win the World Cup,” they say.

As a result of the huge number of permutations of games, this course is still extremely unlikely. Groll and colleagues placed the statistics at about 1 in 100,000.

At the beginning of the tournament, Spain has the best chances of winning, according to Groll. If Germany makes the quarter-finals, it then becomes the front-runner.

The tournament begins on Thursday, when the hosts, Russia, take on Saudi Arabia.