New NFL ‘Expected Return Yards’ stat tackles hidden dynamics of punt and kickoff returns

National Football League (NFL) fans have all witnessed a returner getting tackled a nanosecond after receiving a punt or kickoff. Holding onto the ball, let alone gaining a chunk of yardage, is a huge win. And the odds of a return touchdown are rare. But that’s exactly why it’s a thrill to see a returner beat the odds, weaving through wave after wave of improbability. It’s an art. An extreme outlier in reality. And it can sway the game in a blink of an eye.

Timed to provide new insight as the NFL playoffs get underway, AWS and the league’s Next Gen Stats team built Expected Return Yards. This new statistic uses ML-based technologies to predict in real time how many yards a returner will gain from the moment they catch the ball. This is determined by how well they identify space and break tackles, teammates block and create space, and opponents cover ground and maintain lane discipline.

Read and learn more in these blogs from the NFL’s Next Gen Stats team to find out how returners can add hidden value by setting up their offenses with great field position and a look under-the-hood at how the AWS Machine Learning Solutions Lab leveraged Amazon SageMaker to build separate kickoff and punt return models, a technical challenge given the nuances of each type of return and the limited training samples.