Goldman Sachs has predicted that Brazil will win the 2018 FIFA World Cup, based on its data mining, machine learning, and econometrics systems.
It fed data on team characteristics, individual players, and recent team performance into four machine learning models to analyse the number of goals scored in each match.
The models then learnt the relationship between the characteristics and goals scored, using the scores of World Cup and European Cup matches since 2005.
“By cycling through alternative combinations of variables, we get a sense of which characteristics matter for success and which stay on the bench,” said Goldman Sachs.
“We then use the model to predict the number of goals scored in each possible encounter of the tournament and use the unrounded score to determine the winner.”
Goldman Sachs said its number crunching, 200,000 probability trees, and 1 million simulations produced these results:
- England meets Germany in the quarters, where Germany wins.
- Germany meets Brazil in the final, and Brazil wins.
“For the doubters out there, this final result was cross-checked in excruciating detail by our (German) Chief Economist Jan Hatzius,” said Goldman Sachs.
The image below provides an overview of the 2018 FIFA World Cup prediction by Goldman Sachs.
EA Sports predicts France will win
EA Sports recently predicted that France will beat Germany 4-3 on penalties in the final of the 2018 FIFA World Cup, however.
The prediction is based on a simulation of the tournament using FIFA 18 and new ratings from the 2018 FIFA World Cup update.
France’s Antoine Griezmann and Spain’s Isco will share the Golden Boot award with five goals each, it added.
Spain goalkeeper David De Gea will win the Golden Glove Award.