Scientists at the Alan Turing Institute in the UK have developed an artificial intelligence algorithm that predicts which team is most likely to win. FIFA World Cup in Qatar. The results of previous championships are mainly taken into account. However, important factors such as performance individual footballers. Therefore, it would be interesting if it could be supplemented with another algorithm, developed in 2020 data scientist Carter Booley. In it, he analyzes the different types of passes players can make in order to figure out the best strategies.
It should be noted that this algorithm was not performed for FIFA World Cup in Qatar, nor for any particular championship. It’s just a way to use statistics and computer science develop the best game strategies for football players.
This is mostly based on passes so can be very useful for teams like Spanish selection, whose passing is often one of the keys to his success. Ideally, they should be optimized so that they include minimal energy costs and, in addition, they can be accurately connected until they hit the target. There are no magic formulas; but at least with this algorithm one can help Develop the best possible strategies.
Algorithm for perfect passes even outside of Qatar
It is logical to assume that not all players are the same. There are more or less qualified and more or less trained. However, optimizing their passing strategies can help them all.
This is the goal of this algorithm, which was trained on data from 358,753 passes made in 380 games involving 20 teams. Several factors were taken into account. For starters, if the players were on their own field or on the field of the opposite team. On the other hand, the results are minute by minute and with a complete match. In addition, passes were drawn graphically where the ends of the field would be the X and Y axes. Finally, the type of pass was taken into account: normal, header, cross, corner, launch, goal kick or free kick.
With all this data, artificial intelligence look for patterns associated with a certain type of passing from players with the best results. They found data such as that most passes are missed at a very short distance, below 5 m. In addition, between 15 and 30m “much more passes are made than missed, and after 30m the proportion of passes made drops sharply and the number of passes conceded begins to level off.”
Another key factor was the place on the field where the pass is made. For example, the closer they get to the opponent’s goal, the more missed passes are made. Logically, this is a very important area, so it is important to know which strategies work best here.
Special attention to football players
This algorithm takes into account the individual role of the players. As Buli himself explained at the time, “if the model predicts that a pass will happen with a probability of 0.8 and it will be completed, 0.2 is added to the players’ passing score.” On the other hand, “if the pass was not made, minus 0.8 for players per pass”. This is then averaged over how many passes the player makes to determine average risk score exceeded. “This score allows players to be compared in terms of the risk they take and overcome on transfer.”
Because, logically, it’s not just about knowing which passes are the best. Good players are also needed to fulfill them. It also means that they are capable of taking risks, but not too bold. In the medium term, this is a virtue. And also win a football match. It doesn’t matter if you’re in FIFA World Cup in Qatar or in the regional championship.
Source: Hiper Textual
