Data Mining in football: let's digitize a match and count everyone!

The coach is watching you. The coach remembers. The coach does not forget and does not forgive.

If you saw the movie “The Man Who Changed Everything”, then you already know almost everything. Players need to be assessed by the mass of indicators, and intuition does not always work. With the help of analytics, you can increase the effectiveness of training at times, find new players that will help the team and just improve the level of the game. Analytics taxis .

Football in reality at first somehow reminds RPG without rules where it is necessary to understand. After the introduction of analytics - this is the same RPG, to the hundreds of indicators of which there is an instruction. The coach gets the opportunity to “grow” a real manchkine-cheater.
')
On the field for 90 minutes there are 22 players and the ball. A coach can keep track of only a part of the players - plus his perception is very much subject to emotions. Researches were conducted on how many episodes are remembered: even the most experienced coaches recalled only about 35% of situations, and always around the ball. All the rest is “dead zone”. It is impossible to cover the whole field and understand where someone stood - and did it right or wrong. This requires postmatchevy analysis.

At first, Steve Maclaren - known as the head coach of the England team in 2006 (then the Russian team defeated the English in Luzhniki) - began using video replays as a way to analyze the game. The company Prozone initially engaged in the systematization of video data, selecting and signing the most characteristic moments. This was the case from 1999 to about 2005, when video recognition appeared.

Interview

For 12 years, the company has won the English market and has come to many countries, including Russia. We had a special interview for the national representative Prozone for Habr on the eve of a purely technical lecture on special software, which will be held on March 14 in Digital October (this is an event on Habré ).

- Who already uses this system?

Very many. After the recent merger of Prozone with AMISCO, the customer base has doubled. This is almost all clubs in England, including Arsenal, Manchester United, Man City, Liverpool, as well as such world giants as Real Madrid, Inter Milan, Bayern Munich, Lyon. In Russia, CSKA and Dynamo were the first, then Spartak and Krylya Sovetov . Plus Dynamo Kiev , known for its research center, since the summer of 2011.

- How it works?

There are different types of analysis. The easiest is to take one camera, which removes the match from one point (for example, from the stadium roof). Video data from it is run through analytical services, after which you get accurate data for analysis. If you need to build an “animated simulator” of the match and get the fitness data of the players, you already use special equipment consisting of a set of cameras: this guarantees increased accuracy of recognition of players on the field and their movements.

- Why is postmatchev analysis important?

The coach and his staff want to know everything to improve the game. Standard methods did not give high accuracy. It is very important to provide exact data - otherwise they become unnecessary. It is important not only to remove the data array, but also accurately translate it into the language of the head coach. In the early 2000s, this problem was solved more by video editing; now it is Data Mining with the help of a team analyst.

- What do I get after the match?

We start with an electronic report that can be printed on paper immediately after the game. This is about 1500 events on the field, describing the technical and tactical actions of the players.

There is an interactive platform for viewing matches - it analyzes the technical and tactical actions of the team. It is estimated significantly more: up to 2300 events per game, and analysis can be obtained 12 hours after the end of the match.

It looks like this: the headquarters has spetssoft which pours about 2 megabyte prepared match analysis from the server to the local machine. Further in the interface, you can choose the level of detail for the desired actions and compare various numerical indicators. They wanted to see Ivanov for the whole match - they only saw him in dynamics and numbers. I want to know in which square of the field the team selected more balls? No problem.



There are statistics on their players and opponents' players, a match review (for comparing their own and foreign defenders or two of their attackers, for example), automatic mark points for video editing and analysis (interactive maps of the football field: the directions of tactical-technical actions are visible, where they were performed and what kind of football players). You can compare the command on the accuracy of transmission and other indicators. For example, you can sort the transmission by criteria of success, direction, length of pass, whether you reached the goal, such as (head, canopy) and many other options. More than 40-50 filters per section are available, and all this will be shown in the lecture.

- What, actually, with Data Mining?

The company's pride is a deep match analysis system that requires special cameras for recognition. The simplest thing is that at any moment you can see an “animated” picture with detailed numerical data and the location of the objects themselves in dynamics, which is invaluable for postgame theoretical training.

More difficult - for example, the fitness section, it shows what kind of running work the football player did. The peculiarity is that there are six types of such “exercises”, and many coaches need to work at high speed (more than 5.5 meters per second), which is almost impossible to sort by hand. You can also see when and who is tired: this data goes to the fitness trainer, which is invaluable for assessing the physical condition and exercise plan.

The most important thing is that the trainer can simulate the training process and reveal unobvious “bottlenecks” of the team’s actions in order to improve various critical moments.

- Is it possible to find out if a player is worth his money?

Yes, there is a separate product for scouting. In the season about 10 thousand games are processed. A club that has purchased a license can look at the data on any player for all the time: these are statistics and analytics. You can compare the level of this player and the level of the average player in the Russian championship. For example, if the midfielder makes an average of 4 overhangs in the penalty area, you can immediately assess whether a new player fits this criterion.

Another online product "Trend" allows you to assess the development trend based on all the matches of your team and assesses the dynamics of the players. Prozone gives raw objective data, but does not make expert predictions of the value of players. Forecasts - the task of the manager.

- What kind of iron is required for recognition?

For a technical and tactical analysis without "fitness and animation," you need a regular camera - just get a picture that follows the ball. Football players are recognized by a special software. It is important to get a technical picture, without repetition and advertising, of course (on a regular recording for a number of reasons about 2% of actions are lost).


Sample camera picture

You can recognize old matches on the basis of video recordings: for example, the Everton football club put on sale a box where the cult match against Bavaria was completely disassembled: there is a video and detailed tactical and technical analysis.

Interestingly, Prozone is a certified system that provides 100% accurate data. In the world of football, such a guarantee means something as impossible as “software 100% without bugs” in IT. To achieve this accuracy, you need special equipment at the stadium. Basically - these are ip-cameras that monitor the movement. Put 8 cameras around the perimeter, on the roof according to a special scheme. The server for data collection and the channel for delivery to the sales center are connected.


Grouping cameras in a static complex

There is a light version (with an error of 5-7 percent) - 4 portable cameras on tripods. Conveniently, where you need to quickly turn around and there are operators, for example, on the road. Wings of the Soviets carry such things to every away game.

Static sets of 8 cameras are located at Luzhniki and Khimki Arena in Moscow and at the Lobanovsky Stadium in Kiev.

- How easy is it to learn how to work with the service?

Usually from 1 to 5 days, after a couple of weeks, the system is perceived as "native." Ideally, every club has an analyst who is able to turn the questions of the coach into requests to the system and track what the coach potentially needs, and this direction is already developing in the Russian Federation. In Europe, this has long been used: after all, a coach cannot sit at the monitor for days. We usually have an analyst and team video operator.

- There are special educational programs?

Yes. There are both individual trainings and global educational programs for analysts and team coaches.

- What are the difficulties of implementation?

First, a slightly conservative attitude. Now, of course, there is not a single coach on the market who would say that the system does not like it. Everyone acknowledges that the data is useful and necessary, but, nevertheless, there is some resistance, in particular, due to the fact that in the domestic market the industry of analytics is not developed in comparison with Europe.

- Will it be possible to do without such tools in 10-15 years?

Hardly. In England, for example, almost everyone now uses analysis in one way or another. This is important for the success of the club.

- What are the next steps in the development you see?

Let's try 3D modeling by capturing data from multiple cameras. Already started NHL hockey match analysis tests.

- What of your model can not be repeated?

It is very difficult to repeat the high accuracy of the data: we have a number of key patents and a lot of practice. Large investments will be required to catch up on hardware and software: we are a generation ahead of all other analytical companies. Few people will be able to maintain constant contact with the coaching staff - we are aware of their needs and tasks, we get very high quality feedback.

- Where can I find more technical details?

At a lecture in Digital October on March 14th.

Now about the lecture itself

The lecture will be held by Blake Wooster, a trusted advisor to FIFA, UEFA, Chelsea FC and Real Madrid, the business leader of Prozone. He will talk about the technical side and the specific effect of using the system. Igor Meshchanchuk, sports director of the Russian Premier League, Ilya Rustamov, marketing director for Championship.com and Alexander Ivansky, project manager of InStat Football (in fact, domestic competitor Prozone) are invited to the lecture as experts. A practicing trainer is also expected to be able to explain the situation from his side.

Yes, you can come to the lecture, it is free. Here is the event on Habré , and here is the registration . In the comments to this topic, you can still leave tricky questions to Blake and the experts.