MUMBAI: Its prediction on how the 2014 World Cup in Brazil would turn out (as like most of the footballing world, its choice was the host nation) was off target. Goldman Sachs Research is giving it another shot at using an “eccentric mix” (their term) of economic insight, tenuous correlations and footballing views to determine the country that will take home the most coveted trophy in world team sport.
The financial firm used machine learning to augment typical team level data with player level characteristics. After hours of number crunching, 200,000 probability trees, and 1 million simulations, the results that were thrown up are: France, Brazil, Portugal and Germany will make it to the semi-finals with Brazil beating out Germany in the final.
The match-by-match probabilities – which will be updated throughout the competition – indicate that while Germany is more likely to get to the final, France has a marginally higher overall chance of winning the tournament, and along with Brazil, Germany, and France, Portugal squeaks into the semis, ahead of Argentina.
Brazil and Germany are, in fact, the teams that appear most often in the forecast models produced by economists. The South American country was indicated by Danske Bank, while Germany will triumph in Commerzbank prediction.
EA Sports, which correctly predicted Germany as the 2014 champion, has tapped France as this year’s winner, winning out over Germany in a match largely decided by penalties. Along with its accurate 2014 winner prediction, EA Sports’ Madden franchise has also correctly guessed the Super Bowl winner nine times out of 14.
