Would you trust these guys with your money?
Goldman Sachs’s World Cup Predictions Model: ??
By Phillipa Leighton-Jones and Jon Sindreu, WSJ
Goldman Sachs’s World Cup predictions, outsmarted to some extent by an octopus, have been caught out by reality. A complicated model that predicted Brazil to win the tournament after facing down the Netherlands now looks wanting after both teams were knocked out.
As you may remember, the bank’s economists crunched data on 14,000 past matches to arrive at a 67-page report that confidently calculated the outcomes of all matches, published May 30.
It changed 50% of the teams after the first stage after it became clear reality wasn’t quite matching the historical dataset.
Looking at those original, pre-tournament predictions, only 37.6% of the group stage matches ended the way Goldman Sachs’s original model forecast. That is, it correctly calculated one of three possible outcomes—win, lose or draw—just over a third of the time, hardly better than predicting it at random. From those calculated correctly, they managed to foresee the scoreline 17% of the time, meaning three occasions: Argentina-Bosnia, South Korea-Russia and Algeria-Russia.
(The article is here.)
By Phillipa Leighton-Jones and Jon Sindreu, WSJ
Goldman Sachs’s World Cup predictions, outsmarted to some extent by an octopus, have been caught out by reality. A complicated model that predicted Brazil to win the tournament after facing down the Netherlands now looks wanting after both teams were knocked out.
As you may remember, the bank’s economists crunched data on 14,000 past matches to arrive at a 67-page report that confidently calculated the outcomes of all matches, published May 30.
It changed 50% of the teams after the first stage after it became clear reality wasn’t quite matching the historical dataset.
Looking at those original, pre-tournament predictions, only 37.6% of the group stage matches ended the way Goldman Sachs’s original model forecast. That is, it correctly calculated one of three possible outcomes—win, lose or draw—just over a third of the time, hardly better than predicting it at random. From those calculated correctly, they managed to foresee the scoreline 17% of the time, meaning three occasions: Argentina-Bosnia, South Korea-Russia and Algeria-Russia.
(The article is here.)
Powered by Blogger
0 Comments:
Post a Comment
<< Home