We want to answer a difficult and fun question: What are the chances of each team winning the World Cup in Qatar? To do this, we simulated the tournament tens of thousands of times. This allowed us to calculate the probability each team has of reaching the round of 16, reaching the semi-finals and winning the final.
This is our launch prediction:
PROBABILITY TO REACH EVERY ROUND AND WIN THE WORLD CHAMPIONSHIPS
This data tells us which teams are the favorites and to what extent. They also reflect the fact that the World Cup is quite unpredictable. People expect the favorite to win, but the data says that’s rare: although Brazil are more likely to win than any other team, according to the model, Brazil will win only one in four times.
These probabilities are updated daily by EL PAÍS. Below we explain how the model works, starting with a game.
Simulate the World Cup
By clicking the button below you can use our model to simulate a World Cup and see who wins. Clicking again will run a second simulation and another team is likely to win. Consecutive winners are listed in the table below.
If you play around for a while you will see that the predictions start to reflect the chart above. This will happen slowly, because that’s how coincidence works.
How the model works
Our predictions are the result of thousands of simulations like the ones above, which are only partially random. In each game, the probability that one team or another will win depends on their stats. For example, if Brazil plays Saudi Arabia, the probability that the former will win is around 87%.
The model consists of three parts (details in Spanish):
1. How strong is each team? To determine this, we use two metrics: the team’s recent results (measured using the Elo rating, a chess-derived method now used by the official FIFA rankings) and the quality of its players (measured using their value in euros, using data from the Transfermarkt website).
2. Who wins every game? We trained a model on thousands of games to estimate how likely each outcome is based on the two teams and the strength of their metrics. The model reflects the probability of winning, drawing and losing and even the possible score. For example, in a hypothetical match between Brazil and Saudi Arabia, the most likely outcomes are 2-0 and 3-0, each with a probability of 14%.
3. And to predict the entire World Cup? We simulate every game match by match. We repeat this process thousands of times and come up with 100,000 possible world champions. With this information, we estimate the probability of each outcome. If Brazil wins the tournament in 23,000 simulations out of 100,000, that’s because they have a 23% chance of winning the World Cup.
Predictions by group
The tables below show the probability each team has to win their group, finish second and be eliminated. The top two teams in each group advance to the next round, and the winner of each group tends to have a better chance of progressing to the round of 16.
What do other predictions say?
Similar predictions have been made by others. In the table below, we compare our predictions to those of three other systems: Opta, The Analysts’ statistical model; the odds of 30 betting shops and the predictions of the community-run website Metaculus.
PROBABILITY TO WIN THE WORLD CUP AFTER OTHER PREDICTIONS
Draft: Ignacio Povedano
Interactive simulator: Jose A. Alvarez Iguacel
Development: Carlos Munoz
Statistical model: Kiko Llaneras and Borja Andrino
Coordination: Brenda Valverde Rubio and Guiomar del Ser
Art direction: Fernando Hernandez