Forecast for the 2014 World Cup in Tungsten
The group stage ended at the World Cup, the number of participating teams was halved, and the pairs of playoff participants became known. In this regard, developers from Wolfram Research updated the statistical probability calculation for the remaining matches.
Pre-Wolfram | Alpha uploaded about 200 MB of data extracted from specialized sites. This is, first of all, historical data on 30,000 international matches from 1950 to 2014, including the composition of teams and characteristics of players. This is not only for predicting the outcome of matches, but for the Wolfram | Alpha system to be able to handle search queries related to football.
For example, here are statistics on changes in the growth and body mass index of football players over the past 50 years.
Returning to the analysis of the 2014 World Cup, the model calculates the probability of the outcome of each match based on statistics of past games, including taking into account the advantages of the home field, the advantages of your continent and other factors that emerged after analyzing the historical base. The model then went through training at the last 2000 matches and showed a forecast accuracy of 48%.
After adding teams to the Elo-ratings model, the accuracy increased by 58.3%, and for elimination matches - 75.7%. This is quite enough to calculate the probability of the outcome of the 2014 World Cup.
So, after the group stage, the probability of winning the tournament is distributed as follows.
Compared with the previous forecast, the chances of the Netherlands have risen sharply (thanks to a major victory over the favorite).
The most likely pair of finalists are Brazil and the Netherlands.
The entire grid of the expected outcomes of the playoff games is shown in the diagram.
Another set of charts shows the probability of winning (blue) or losing (orange) for the 9 most rated teams at each stage of the playoffs.
At the group stage of the 2014 World Cup, Wolfram | Alpha forecast accuracy was 62.5% (the engine correctly calculated Costa Rica's victory over Italy, a draw in the match between Germany and Ghana, a draw from Brazil and Mexico, as well as several other unobvious outcomes). Let's see how the model shows itself in the playoff matches.