So much for the unpredictable nature of the beautiful game. Goldman Sachs Group Inc reckons Brazil will win its sixth World Cup, basing its forecast on data mining, machine learning and econometrics.
The investment bank is the latest to jump into the excitement before the soccer championship kicks off this week. It used 200,000 statistical models, sifted data on individual players and recent team performance and ran 1 million simulations of the tournament.
As a result, it predicts that Brazil will lift the trophy on July 15. We should note that Goldman also tipped Brazil in 2014 (forecasting a 3-1 win over Argentina in the final). But Brazil stumbled in the semi-final back then, losing by a whopping 7-1 to eventual champions Germany.
“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. By cycling through alternative combinations of variables, we get a sense of which characteristics matter for success and which stay on the bench.
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...