Drafting an NFL dream team with AWS

How the Seattle Seahawks use technology from AWS to take the guesswork out of draft season and unlock game winning strategies year round.

What’s one of the secrets to building a successful National Football League (NFL) draft class? Believe it or not, the answer lies not just on the field of play but in harnessing the collective expertise of coaches, scouts, and analytics to acquire knowledge about players.

We sat down with Seattle Seahawks’ head of research and analytics, Patrick Ward, to give an exclusive behind-the-scenes look at how the team is harnessing the power of collaboration with Amazon Web Services (AWS) to better develop game-winning formulas.

Making the switch from analog to digital

Data analysis has come a long way since Ward began his career in the football industry over a decade ago. When he first started, the data collection process was entirely manual. After games and practices, he and his team would work tirelessly through the night to build reports gathered from multiple technology systems and sources—sifting through things like personal laptops, spreadsheets, text files, and multiple databases. It was a lot of legwork.

“Every night we would run a report, join these datasets, go to these folders, grab these datasets, fit this model, run this model. Everything was dependent on the person who was running things.” Ward admits that without a reliable system and way to share queries with staff in other departments, he and his team often risked the chance of delivering disconnected data and siloed analytics reports.

But the NFL is always evolving, and the league started shifting toward adopting more analytical approaches to understanding the game. As a data-driven organization, the Seahawks were looking to gain a competitive edge by gathering insights faster from an explosive growth in data volumes and types.

By leveraging AWS technologies, the Seahawks are able to shift their operational approach. They’ve successfully consolidated their data collection, storage, and catalog into one single data lake—with personalized web applications that help pinpoint unique player perspectives at the touch of a button. Now, with everything in one place, they are able to easily streamline and share information across the organization without staff members having to rely on an analyst to build new reports. For Ward and the team, this was a challenge worth solving.

“Data is only increasing. So, putting systems in place to handle this data is critical to stay on the cutting edge of player analytics,” says Ward.

Earning a seat at the draft table

Since moving over to AWS, the Seahawks’ drafting formula has evolved. Take a peek in the Seahawks draft room and you’ll notice Ward and his team have a seat at the table—a far cry from the once exclusive “scouts only” rule. During draft season, you’ll find analysts front and center at every meeting, leveraging and interpreting personalized data collected by AWS custom web apps that help identify prospects who may have otherwise fallen through the cracks.

“There are thousands of draft-eligible players, but a scout can only watch so many players,” Ward explains. “But [with AWS], we can run models against all players and identify unique guys that stand out or bring people into the fold that haven’t gotten the same amount of evaluation as other players—because they played at a smaller school or played in a smaller program.”

Between the draft selections, undrafted free agents, and rookie minicamp, the Seahawks end up bringing in roughly 25 prospects each offseason. Similar to players like Doug Baldwin or Brian Mone, there many athletes in the back end of the draft and into free agency that have an opportunity to get on the field, make their mark, and have a positive career.

“A lot of it for us is being able to construct systems that can aggregate data across all potential draftees and then build and leverage models to help compare talent, organize talent, [and create] short rankings for players—ultimately, [we’re] trying to forecast what we think this player may become in the NFL,” says Ward.

Using AWS to build a future-proof infrastructure

After experiencing the benefits through a collaborative work stream, the Seahawks introduced these systems in other ways throughout the organization. Today, they are utilizing data lakes to gain a deeper understanding of player capabilities. Using the data lake cross-functionally has helped Ward and his team maximize the value of data, giving the Seahawks a competitive edge on and off the field.

So, what kinds of information is his team leveraging to predict success? Applied physiology, for one. Custom-built dashboards geared toward the draft easily organize metrics that better help Ward evaluate things like health, risk tolerance, and the best ways to practice a player. The data is then shared directly with the appropriate decision-makers where it is evaluated and analyzed.

The Seahawks have built a considerable database around the structure and contents of practices that allows them to create unique models specific to their coaching staff, players, and natural events throughout a given season. Using AWS, they are able to ingest a practice script, run a model against it, and, as a result, give the staff a report on estimated training demands given what we know about that day’s events. This script includes parameters coaches have specified in drills, even down to the individual player level and potential risks to manage. This new level of insights has allowed them to have unique discussions about the contents of practice that were never previously not possible.

“We’re getting more complex and diverse types of data. We need a system that allows us to create an infrastructure that is future proof. [AWS technologies] allows us to have a data lake that can ingest everything from simple count data to tracking data to video data. We are able to build purpose-built layers around that that allows analysis to happen quickly.” Says Ward.

When it comes to data analysis, speed is key. The Seahawks’ centralized data lake has led Ward and his team to insights that can be used to help solve a variety of problems. With information in one place, they are now able to quickly construct individualized web apps to answer key questions and meet the needs of every coach.

“Being agile enough to meet [the coaches] needs while building something more, that is future proof. And being able to provide other coaches with similar information is critical,” Ward says.

Leaning into decision-making data

When it comes to football, data is power. And it’s evolving, fast—with more and more complex datasets aggregated daily. The benefit? Time and agility.

“[AWS technology] quickly gets us from ‘What are we going to do with all of this data?’ to directly putting it in the hands of the end user, the decision makers, and the people who need to interact with it,” Ward says. “Edges in sport are fleeting—as soon as you feel like you’ve got an edge, 60 days later, everybody’s got that same edge. You’ve got to move fast and iterate quickly.”

So, what exactly is the secret to a successful draft? Well, if you ask Ward, you might just get your answer: “Everybody is looking at the same types of information. Everybody’s trying to ask the same questions. The unique part is the ways in which we use AWS to reveal deeper insights and bring all of that information together.”

Learn more about how the Seattle Seahawks use AWS: https://aws.amazon.com/sports/nfl/seattle-seahawks/