Juan Busso describes what surprised him most while developing the Match Momentum model: coming from a biology background, he was used to thinking in continuous probability distributions rather than discrete categories, and applying that mindset to football produced unexpected results during validation. High threat or momentum values sometimes appeared in situations that validators had not previously considered dangerous, but on review they agreed the model had correctly flagged something real.
- 01
Busso frames the shift as moving football analysis away from fixed 'boxes' or categories toward continuous probability distributions, drawing on his biology training.
- 02
The surprising cases emerged specifically during the validation process, where football experts checked the model's high-threat outputs against real match situations.
244 words · auto-generated from the episode video
21:39And so on a followup, you know, as you guys have been going through this development process, right, around kind of honing in, you know, to really make sure that the match momentum reflects the flow of the game, you know, as you went through that process, was there anything surprising or something that you didn't expect as you worked through that process? Yeah, Juan, I'll give you some of the surprising things that we found. >> Um, to be honest, I think that the we when we were developing these principles like it was very I would say for me interesting to see I
22:20my background is in biology. So I come from a place where there are no boxes basically. So everything is in a distribution. Everything is kind of there are probabilities. So uh this is a bit the for me the surprise that in football like uh bringing this into football and trying to you know transform the the box concept into these uh probabilities or or basically continuous distributions uh generated a lot of interesting situations outcomes during the validation process where the there will be a high let's say threat value or high momentum and and the
23:00validators would go and check and then they would be like, "Oh, true. Now it makes sense." But it would be like uh something that sometimes situations would pop up that were not perceived before. And when you actually look at
Data ScienceSports AnalyticsWorld CupPerformance Analysis