2018 World Cup Predictions - Using AI

future of soccer.jpg
  • Last week, Goldman Sachs released “2018 – The World Cup and Economics."  The report said “while selecting the best starting eleven requires human judgment and experience, choosing the best variables to predict the outcome of a game is better left to a statistical model. Or more precisely, 200,000 models: harnessing recent developments in “machine learning,” we mine data on team characteristics and individual players to work out which factors help to predict match scores ... We then simulate 1,000,000 possible evolutions of the tournament to gauge the probability of each team progressing through the rounds.
  • “we feed data on team characteristics, individual players and recent team performance into four different types of machine learning models to analyze the number of goals scored in each match. The models then learn the relationship between these characteristics and goals scored, using the scores of competitive World Cup and European Cup matches since 2005.”
  • Predictions: Brazil will win its sixth World Cup title—defeating Germany in the final; France has a higher probability than Germany of winning the World Cup. But its (bad) luck in the draw sees it meeting Brazil at the semi-final stage, Germany is forecast to defeat England in the quarter finals; Spain and Argentina are expected to underperform, losing to France and Portugal in the quarter finals, respectively
  • The report is here


  • Separately, researchers shared the following at the Cornell University Library website, “we compare three different modeling approaches for the scores of soccer matches with regard to their predictive performances based on all matches from the four previous FIFA World Cups 2002 – 2014.
  • "The model slightly favors Spain before the defending champion Germany.” 
  • Brazil was ranked third, France fourth, and Belgium fifth.
  • The results were based on 100,000 simulations of the 2018 World Cup.


  • Forecasting the outcome of an event such as the World Cup is a complex process because of many unexpected variables - such as Spain firing its coach two days before the start of the games. 
  • AI/machine learning may reduce some of the “guess work” in predicting the outcome of the 2018 World Cup – but the challenge is still significant.
  • Bottom line: Debate the predictions, watch the games and have a great time

More AI resources here

Paul Dravis