Machine Learning has predicted Germany will win the 2018 World Cup.
The research conducted at the Technical University of Dortmund in Germany combined machine learning and conventional statistics, a method called a random-forest approach, to find the most likely winner of the football tournament.
Bookmakers suggest Brazil is the favourite to win the FIFA cup, with a probability of 16.6 per cent.
But according to a report in the MIT Technology Review, artificial intelligence (AI) is tipping Germany to take home the trophy.
The random-forest technique has emerged as powerful method of analysing large data sets while reducing the flaws of other data-mining methods.
It is based on the idea that some future event can be determined by a decision tree in which an outcome is calculated at each branch by reference to a set of training data.
But decision trees suffer from a pitfall in the latter stages of the branching process, where decisions can become severely distorted by training data that is sparse and prone to huge variation.
The random-forest method does not calculate the outcome at every branch but calculates the outcome of random branches multiple times, and then bases its final result on an average.
So by predicting the result of the matches in the round of 16, the quarter and semi-finals the study was able to predict which teams would be in the final.
From the early stages, the data identified Spain as the most likely winner, with a probability of 17.8 percent.
But by allowing the random-forest approach to simulate the whole tournament it predicted a Brazil Vs Germany final, with Germany having a 64 per cent chance of winning the 2018 World Cup.
The team simulated the entire tournament 100,000 times.
The data concluded that if Germany makes the quarter finals, they have the best chance of winning the tournament.
Andrea Groll, who headed the research, said: "According to the most probable tournament course, instead of the Spanish, the German team would win the World Cup."