Match Momentum was built to capture threat and danger a team creates on the pitch, not just possession or territory in the final third. FIFA's performance analysis and data science teams wanted a model that could show when a team without the ball is still the more dangerous side, since traditional possession stats miss this. The developers point to real examples, like Atletico Madrid winning games without dominating the ball, and Cabo Verde creating strong chances against a possession-heavy Spain, as the gap their model tries to close.
- 01
The chapter frames the model as a collaboration where football experts describe what momentum and threat look and feel like, and the data science team then works to identify that in tracking data and render it graphically.
- 02
The speakers contrast their approach with another existing momentum or threat product from a different data company, though they do not name it.
621 words · auto-generated from the episode video
5:50That's so fascinating and and and makes total sense. I think you know coming from a background in you know software from more of a tech perspective but having been a footballer myself seeing kind of the intersection of these two worlds is uh I continue to find fascinating as data has become more and more integrated into the game you know as over the last you know decade or two. And so if we kind of dig in here, you know, with maybe the first question, which is, you know, given that answer Aaron you just brought up about storytelling, right, through data and analytics, what, you know, what problem are you trying to solve with the concept
6:30of of match momentum and kind of what motivated the development around it? >> Sure. So I'm happy to to give a bash at this. Um, look, we want to be able to tell the most honest and truest story of a match that's happening, right? And we know that each team has their own style that they want to play. We know that teams have nuances and variations of the things that they do on the pitch. [snorts] We can measure them in fairly basic ways by counting things, right? We can measure them based on positionally where players are positioning themselves. and commentators for example and experts on TV will identify these anyway but actually what is it that we
7:12can use to really try and identify and show that okay maybe this team doesn't have the ball but when they do have the ball they're creating a lot of threat and they are becoming really dangerous right and that's where you know myself and Juan work together really closely on trying to take knowledge from the experts about what does it look like what does it feel like um with regards to momentum, with regards to threat, identify what that potentially looks like in the data and then represent that graphically. So I know obviously previously on the pod you talked about um another kind of uh uh uh data set or data company um that uh had their version and our approach was was
7:54slightly differently which I'll I'll let Juan explain in a minute. But one of the key and most important things for us to us was it's not necessarily just about having the ball in the final third. And that's probably what most people think about momentum. You can use two extreme examples. These are the two examples I always use. Why is it always that Atletico Madrid win games when they don't dominate the ball? >> Whereas because they create threat in the right moments, right? As an extreme example. We saw that in this tournament with Carbo Verde. Why do they for instance create great chances without having a lot of the ball for instance against Spain who completely dominate the ball right and although our model um will identify naturally that Spain have
8:35a lot of threat because they do um that isn't to say that at any no point other than when Spain don't have the ball that then for instance Cabo Verde or in lots of cases Atletico Madrid have the ball right so that was a a huge important piece for us to try and overcome um that was beyond the basic kind of looking way of looking at it where it's just if you have the ball in the final third therefore you control the greatest amount of chances that is true in most parts but it isn't always true and how do we make sure that we can represent as close to the truth as possible Juan
Data ScienceSports AnalyticsWorld CupPerformance Analysis