The big analysis project we did on set piece and open-play cross-optimization brought to life a lot of match data we were analyzing. We managed to make our analysis operational and made it work on an ongoing basis as an automated process that has led to tangible success on the pitch, especially as coaches are actively using it to make decisions in training and designing the best tactical setup for matches. I'm saying it has been successful on the pitch because, in both the 20-21 and 21-22 seasons, we have seen a dramatic improvement in set-piece performance and open-play cross performance from both a defensive point of view and an offensive point of view.
We have two main sources of data. First is the event data, which is the data of every single event that happens during a game. So, every pass, every shot, every bull carry, a clearance interception, and even red cards and yellow cards from the referee. It’s any event that is relevant in a game of football. The other source of data we get, which has higher potential, is tracking data, which provides information about players, ball positioning, and speed throughout the game at 25 frames per second. So, essentially, for each second, you get 25 observations for the ball and for each player, which amounts to roughly 3 million rows per game.
Managers have a key role role in determining which data is prioritized and how that data is used
Chelsea’s data team uses two main sources: event data, which is every relevant action taken in a game, and tracking data, which provides information about players and ball positioning.
Chelsea’s data team chooses long-term projects based on what will result in regular usage by the team and how much time they have to ensure that the project is both effective and fully-functional when it is put in place.
About Federico Bettuzzi
How to Become a Data Scientist in 8 StepsFind out everything you need to know about becoming a data scientist, and find out whether it’s the right career for you!
How to Become a Data Engineer in 2023: 5 Steps for Career SuccessDiscover how to become a data engineer and learn the essential skills. Develop your knowledge and portfolio to prepare for the data engineer interview.
How to Become a Data Analyst in 2023: 5 Steps to Start Your CareerLearn how to become a data analyst and discover everything you need to know about launching your career, including the skills you need and how to learn them.
How Data Science is Changing SoccerWith the Fifa 2022 World Cup upon us, learn about the most widely used data science use-cases in soccer.
Sports Analytics: How Different Sports Use Data AnalyticsDiscover how sports analytics works and how different sports use data to provide meaningful insights. Plus, discover what it takes to become a sports data analyst.
Inside the Generative AI Revolution
Martin Musiol talks about the state of generative AI today, privacy and intellectual property concerns, the strongest use cases for generative AI, and what the future holds.