Goldman Sachs predicts the 2014 World Cup winner

May 29, 2014 2:41 pm

By Hossam Abougabal

With the tournament fast approaching, people across the globe are placing their friendly bets on which team will win and progress the furthest to this year’s finals in Brazil.

For most part, predictions are based on the understanding of ‘the beautiful game’, rather than quantitative and tangible research. Although those in love with the game will argue that it is impossible to foretell any score, as football is far from predictable, betting agencies and other institutions have figured out formulas based on years of results to try and calculate the outcome of each game.

Goldman Sachs released a statistical formula in its recent report, entitled: The World Cup and Economics Report 2014, for predicting the outcome of the 2014 World Cup. It constructs a stochastic model that generates a distribution of outcomes for each of the 64 matches of the 2014 World Cup, from the opener between Brazil and Croatia on June 12 in São Paulo through to the finals on July 13 in Rio de Janeiro – the firm predicts a final match between Argentina and Brazil, with the final score 3-1 in Brazil’s favour.

The explanatory variables in the regression analysis are as follows:

1. The difference in the Elo rankings between the two teams; the Elo ranking is a composite measure of a national football team’s success that is based on the entire historical track record. Unlike the somewhat better known FIFA/Coca-Cola rating, the Elo rating is available for the entire history of international football matches

2. The average number of goals scored by the team over the past ten mandatory international games

3. The average number of goals received by the opposing team over the past five mandatory international games

4. A country specific dummy variable indicating whether the game in question took place at a World Cup. This variable is meant to capture whether a team has a tendency to systematically outperform or underperform at a World Cup

5. A dummy variable indicating whether the team played in its home country

6. A dummy variable indicating whether the team played in its home continent, with coefficients that are allowed to vary by country


It is indeed difficult to forecast any game of football, but such research has proven to provide the most accurate form of predictions and, in Europe, the betting industry often conducts similar studies, which are approved by gambling commissions.

Having said that, although the report offers a highly sophisticated methodology, it recognises that this is a purely statistical approach and, in the game of football, many will tell you that the passion of the crowd and emotions on the day are the biggest variables in determining the final outcome.