You are using an older browser version. Please use a supported version for the best MSN experience.

Seattle Seahawks’ deep dive into analytics starts with a ‘data lake’ built by Amazon Web Services

Geekwire logo Geekwire 11/19/2020 Kurt Schlosser
a crowd of people watching a baseball game: Seattle Seahawks quarterback Russell Wilson. (GeekWire File Photo / Kevin Lisota) © Provided by Geekwire Seattle Seahawks quarterback Russell Wilson. (GeekWire File Photo / Kevin Lisota)

It’s trendy these days to turn to sports data analytics for a deep dive into how a team is set up to compete and what metrics make the most sense for how players perform in a game. For the Seattle Seahawks, that dive starts with a “data lake” built with Amazon Web Services.

A data lake is a “centralized repository that allows organizations to store, govern, discover, and share all of their structured and unstructured data at any scale,” says Werner Vogels, chief technology officer at Amazon and author of a new blog post that should make any football fan geek out far beyond the X’s and O’s of conventional analytics.

Amazon expanded its partnership with the NFL when it secured a deal with the Seahawks last year to become the team’s official cloud services provider.

Vogels, a fútbol fan at heart, has a growing passion for American football mainly because of the way technology is impacting the sport’s progression and how the Seahawks most notably are at the forefront of adopting new tech such as machine learning, internet of things and serverless architecture to make improvements from player safety to performance on the field.

It all starts with data, Vogel writes, and the impact is felt across a number of key areas related to the team:

  • Talent evaluation and acquisition: Traditional scouting is supplemented with AWS analytics as the Seahawks collect data such as the size of the school a player comes from, position they play, and roles they’ve played within that college team’s style of play. Along with data about the Seahawks, including their style of play and current players on the team, an ML model evaluates whether or not a player is a good fit. The modeling is used during the NFL draft and in free agency.
  • Player health and recovery times: Each player receives an initial baseline health assessment, and the team collects ongoing information about players, like exertion level, trend of reps in practice, explosive movements, how often they work out, and more. Tracking this data allows the Seahawks to maximize a player’s gains, reduce soft tissue injuries, and better understand their load from practice to games. With the data lake on AWS, the information is more easily accessible in one place.
  • Game planning: Video analysis is key to the prep work that goes into analyzing talent or getting ready for an opponent. The Seahawks have worked with the Amazon Machine Learning Solutions Lab to build custom ML models that automatically identify players on the field and the type of play. Seahawks data scientists can load plays from a player’s career and see what they’ve been most successful doing, which could help integrate that player into certain schemes and maximize their results faster than before.

It’s debatable how much all of this tech and data actually equates to wins. While we know, as we’ve heard somewhere, that the separation is in the preparation, few fans will likely be wishing for better data analysis if the Seahawks don’t just come out and win with the human talent assembled.

But as far as Vogels is concerned, you don’t have to fish far for answers as to why the team is tied for first place in the NFC West — the Seahawks are “aided by all of the meticulous preparation put into every game day, some of which is coming directly from this data lake.”

Related:

AdChoices
AdChoices

More from Geekwire

image beaconimage beaconimage beacon