Machine Learning - eBook (EN)

The NFL "goes long" on machine learning

Issue link: https://read.uberflip.com/i/1301581

Contents of this Issue

Navigation

Page 4 of 18

5 WHAT HAPPENED? Completion Probability is measured using more than 10 different in-play factors starting with data transmitted by RFID chips in the football and on players' shoulder pads all collected by RF receivers around the stadium. In the case of Rodgers, the data shows the pass traveling 60.3 yards in the air from the location of Rodgers at the time of the throw to Allison at the time of the catch. Rodgers had 2.1 yards of separation from Jonathan Bullard when he released the ball, and Allison had 0.9 yards of separation from Kyle Fuller at the moment of the catch. The data behind the stat All of those factors, among several others, had a direct relationship with the likelihood Rodgers' pass would be complete or incomplete. We can evaluate these relationships by plotting each in-play factor against the actual completion percentage to better understand each factor's effect on the outcome of a play and contextualize the difficulty of a throw. Let's review some of these factors and examine how the predictive models were trained. By Matt Swensson, Vice President of Emerging Products and Technology of the NFL

Articles in this issue

view archives of Machine Learning - eBook (EN) - The NFL "goes long" on machine learning