FIFA World Cup 2022: All the lore

The world Cup 2022 has come to life – without theItaliaas we know, and Not without controversy The first surprises have already been booked: the defeat of the candidate Argentina against the less noble Kingdom Saudi Arabiafor example, or Frightening Manshaft against the Japan. In short, the eventful World Championship presents us with some surprises and overturned many expectations. And if we refer to predictions, it is impossible not to think about prediction algorithmsIn the Data science: It is these days, for example, the news that a team of scholars came out Alan Turing Institute Developed a prediction model that, based on 100,000 simulations of World Cup matches, predicted that the national team would be Brazil To lift the World Cup on December 18 next Lusail Stadium. But science and technology are not only interested in these aspects, which probably interest bettors more than fans: today, in fact, science and technology are dramatically changing football, supporting coaches and athletes more closely than ever before to develop better tactics and improve performance. Numbers and algorithms at hand.

Here’s how it ends

Let’s start with the most “trivial” and certainly the most dated aspect, which is the predictions for the 2022 World Cup. He says David Adams in Recently posted piece naturesfor decades statisticians Football participants focused almost exclusively on the number of goals scored and conceded by a team and on finding the best model to predict them. Variables of these methods are still used today to predict the outcome of matches: one of them, for example, assumes that the number of goals scored and conceded is distributed around a certain mean value, and was developed by a team of epidemiologists from ‘Oxford university. We succeeded in this, since he predicted (correctly) that the Italian national team would defeat the England national team in the final of the European Football Championship 2020 (more precisely, he predicted the highest probability of this in terms of goals scored and conceded ); But not only that: He’s also made it to six of the eight quarter-finalists. “Basically we want to give every team an offensive and defensive ‘result’ – always explained a naturesAnd the Matthew benOne of the developers of the form – Calculated starting from the total number of goals scored by each team and the strength of their opponents: by entering these parameters we get a set of equations that must be solved to calculate the two scores, and it becomes relatively easy to make predictions for each match”.

The Mold We mentioned at the beginning, referring to this year’s World Cup, it works in much the same way: its creators gave each team an offensive and defensive score, and removed “home farmer” (a parameter that increases the probability of winning the home team, which, of course, applies in this case to all teams except Qatar) and You feed on the algorithm The results of many international friendlies before the world. With this tool, they simulated about a hundred thousand matches and thus came to the conclusion that the green and gold national team would be the best out of the others. Another group of researchers from University of InnsbruckIn Austria, with A A slightly different model. Insurance company LloydInstead, use a file another model (who correctly predicted the victories of Germany and France at the 2014 and 2018 World Championships) came up with the prediction that this time it would beEngland To win (beating Brazil in the final). There are still different conclusions, finally, for the Penn group, whose model is capped instead Belgium. If the algorithms don’t agree either…

From Match analysis for scouts

But, like we said, expectations are only a small part of the pie. Not even the freshest, at least for those who play football as professionals. “Science and Technology – tell us Fanny de ViboFootball data analyst for Italian Football Federation (Figc, i.e. for our national football teams) – They enter football in at least four main areas: the so-called match analysis, The Scouts Injury prevention, rehabilitation and finally all aspects of a larger nature Big company.” Di Vipo explains that in analyzing matches, data from cameras and the GPS worn by players is used to obtain variables of interest and build up game patterns: who is the stronger headbutting player, for example, who makes more passes Which side is more likely to score (or concede) a goal. “The cameras give us details of the position of the players and the ball thirty times a second – he explains Matthew Giacalonewho dealt with him Match analysis toInter – It is a huge amount of data, which we process and extract indicators from which we then share with the technical staff of the team. Our information is combined with video clippings from matches and training sessions and compiled into a video that the manager can then review and show to the team.”. Not only: with this data – continues Giacalone – It is possible to build Offensive danger indicator And it’s basically a linear combination of different variables – eg chances you had, number of crosses, ball possession, etc.. Even if winning the game is another story: “Football is a completely different sport than others, for example, from basketball or baseball – De Vibo says again – As is Continuous game low score: One ring is enough, the ball which is ten centimeters or more, to set up a full game. It is precisely because of this high “volatility” of the game that making predictions is very difficult. Basketball, for example, is different: chance can have a certain weight in scoring a shot, but given that many points are generally scored, it is reasonable to expect – and indeed is – the “high numbers” effect that almost always causes the team The strongest wins.

The big data It is also very useful in the process Scouts: Thanks to these tools – Giacalone says – We are able to download and analyze the benchmarks of hundreds of players and understand which one is better to buy, both from an economic point of view and in terms of technical characteristics. We can refine the search to 3 or 4 players and then tell the coach which one is the best.”. Di Febo takes care of this: “At the moment we aim to screen all potential international players – explains – We scout players from under 15 years old onwards, examining all the data we get from match lists: appearances, goals scored, and achievements. This way we try to identify the most interesting names and go and see for yourself..

Then there is the issue injuriesAnd even then, technology plays an essential role: the data that footballers collect does, in fact, say a lot about their state of health. “If we knew that for example The right player has an acceleration of 35 m/s² – De Vibo says again – Instead we see that in training it can’t reach that acceleration, we can imagine that something might be wrong. We are also able to monitor any excessive and too close efforts and alert the technical staff that the athlete may be injured.”. Finally the whole part Big companywhich are of equal importance in professional football: “We can make predictions and assessments, for example, about the rewards players receive Giacalone explains. But also about which teams you buy (or sell) the most from, what percentage of foreign players etc..