An artificial intelligence (AI) predicts the best strategies of soccer players |

Researchers from the Alan Turing Institute in the UK have developed an AI algorithm to predict which team has the best chance of winning the World Cup in Qatar. It mainly takes into account the results of previous championships.

However, important factors such as the performance of individual players are left out. It would therefore be interesting for it to be supplemented with another algorithm, developed in 2020 by data scientist Carter Bouley. He analyzes the different types of passes that players can make to calculate the best strategies.

It should be noted that this algorithm was not made for the World Cup in Qatar or for a specific championship. It is simply a way of using statistics and computer science to develop the best playing strategies for soccer players.

It is mainly passing based, so it can be very useful for teams like the Spanish national team, whose passing game is often one of the keys to their success. The ideal is to optimize them so that they involve a minimum of energy consumption and that they can also be chained with precision until they end up in the target. There is no magic formula, but at least this algorithm can help design the best possible strategies.

The algorithm for the perfect passport, even beyond Qatar

Of course, not all soccer players are the same. They are more or less qualified and more or less trained. But optimizing their passing strategies can help them all.

That’s the goal of this algorithm, which was trained using data from 358,753 passes made in 380 matches involving 20 teams. Several factors were taken into account. First of all, it must be determined whether the players are on their own or the opposing team’s side. For another minute by minute result and full match results. In addition, the passes were drawn graphically, with the ends of the field being the X and Y axes. Finally, the type of pass was taken into account: normal, header, cross, corner, throw-in, goal kick or free kick. .

With all this data, artificial intelligence was put to work to search for patterns that linked a certain type of pass with better results. They discovered data that a large proportion of passes are missed at a very short distance, less than 5m. Furthermore, between 15 and 30 m, “ there are far more successful passes than missed passes, and after 30m the proportion of successful passes drops dramatically, while missed passes start to level off“.

Another key factor was found to be where on the field the pass is made. For example, the closer they get to the opponent’s goal, the more missed passes they make. Logically, this is a very important area, so it is important to know which strategies work best in this place.

Special attention for football players

In this algorithm, the individual role of the players is taken into account. As Bouley himself explained at the time, “ if the model predicts that a pass will occur with a probability of 0.8 and it is made, 0.2 is added to the player’s pass score“. Opposite to, ” if the pass is not made, minus 0.8 for the players pass rating”. The average is then calculated on the number of passes made by the player to define an average pass risk score. “This score makes it possible to compare the players through the risk taken and passed in the pass“.

Because logically, it’s not just a matter of knowing which passes are the best. You also need good players to execute them. It also means that they must be able to take risks, but without being too bold. There is virtue in the middle ground. This also applies to winning a football match. It doesn’t matter if you are at the World Cup in Qatar or in a local championship.

Show Hide the table of contents

Leave a Comment