Skip to main content
Go to the home page of the European Commission (opens in new window)
English English
CORDIS - EU research results
CORDIS

Soccermatics: data for football fans and clubs

Periodic Reporting for period 1 - SOCCERMATICS (Soccermatics: data for football fans and clubs)

Reporting period: 2017-08-01 to 2019-01-31

The project Socceermatics' goal was to develop tools for both teams and fans for the analysis of football.

During the project we developed the most advanced algorithm for evaluating players. Every pass, tackle and shot they made during a match was assigned a value based on the increase in or decrease in probability of scoring it produced. Every time a player touches the ball during a match, the interaction is assigned a value which is then used to calculate his or her performance. For example, if the player scores a goal, he gets 1000 points. Similarly, if a player makes a very good pass forward towards the goal, it increases the chance of a goal by 20%. Then the player would get 200 points. And so on.

We turned our algorithm in to an app, now available at

twelve.football

where fans could look at the performance of their favourite players. The app became very popular during the World Cup with 1000 visitors per day to our website.

We are closer to market in several ways. I am now working together with two tech entrepreneurs (Marcus Lådö and Lars Ekman) to develop products based on the basic algorithm. We have a working fantasy football game and app based on our evaluations. We have been developing a chatbot which, instead of just stating what happens during a match, can chat with fans. The company we developed continues to grow and we are now in the next stage of bot development.

We have also had a lot of contact with football clubs about our methods. The methods we apply in our work comes from analysis of the movement of animal groups, such as fish schools and bird flocks, carried out during the original ERC financed grant. Through local interactions, these groups can form very effective collective patterns. In our contact with clubs, we have looked at how we can organise football formations using the same principles. Simple interactions between players can produce more effective collective organisation.

From April 1st 2019, David (the PI) will continue the work at Hammarby football club in Stockholm. The idea there is to be involved at all levels of the club, from working with the players on 'collective motion' to developing, together with Twelve, analytics that are accessible to fans.
My booklet 0 0