Big Data Bowl

Welcome to the NFL’s Big Data Bowl

The annual sports analytics contest from NFL Football Operations challenges members of the analytics community – from college students to professionals – to contribute to the NFL’s continuing evolution of the use of advanced analytics. The crowd-sourced competition uses data and technology to spur innovation that results in creating new insights, making the game more exciting for fans and protecting players from unnecessary risk.

Powered by Amazon Web Services (AWS), contestants use traditional football data and Next Gen Stats to analyze and rethink trends and player performance, while also advancing the way football is played and coached. The Big Data Bowl aims to engage and empower the football analytics community to drive innovation.

The Fifth Annual Big Data Bowl

Using Next Gen Stats powered by Amazon Web Services (AWS), the theme of the 2023 Big Data Bowl is to devise innovative approaches to analyzing pass blocking and pass rushing performance across the NFL. Participants have access to data from the 2021 season analyzing quarterback dropback pass situations, which include snap-to-pass release timing as well as sacks and scrambling plays. As in the 2019-2022 Big Data Bowls, the 2023 Big Data Bowl is hosted by Kaggle, the world’s largest community of machine learning practitioners, learners, and researchers.

Using this real-time data across a wide variety of players, plays and situations, participants are asked to identify metrics to assess offensive and defensive performances on both an individual and team basis. Participants will also be able to use PFF Scouting data, which features play, player and game characteristics derived from film analyses.

"Throughout four outstanding years of competition, we are increasingly impressed by the innovative data that is generated from our sports analytics community in the Big Data Bowl," said Michael Lopez, NFL senior director of football data and analytics. "Being able to engage with our fans in such a robust and creative manner has helped to continue to grow the game of football while also creating opportunities for our fans to pursue jobs throughout the league."

The Big Data Bowl Structure

Contestants in each year’s Big Data Bowl compete for prizes ranging from game tickets to cash, including a $100,000 prize for the competition. Even if participants do not finish as a finalist, the Big Data Bowl has served as a pipeline with NFL teams or their affiliate vendors.

Stay tuned to hear more about the next Big Data Bowl competition by following the NFL Football Operations Facebook and Twitter accounts.

The NFL’s Inaugural Big Data Bowl

Congratulations to the winners of the NFL’s inaugural Big Data Bowl. Finalists presented their findings to members of the NFL league office, team executives, industry-leading representatives and league sponsors at the NFL Combine. The two grand prize winners receive four tickets to a 2019 regular season NFL game and a $1,000 NFLShop.com gift card.

Congratulations to the eight finalists for the NFL’s inaugural Big Data Bowl. The finalists, determined by a panel comprised of NFL staff and club analytic personnel, receive a 2-night trip to the NFL Combine in Indianapolis on Feb. 27, 2019. 

At the Combine, they’ll have an exclusive opportunity to present their findings to members of the NFL front office, team executives, industry-leading representatives and league sponsors. Two Grand Prize winners will receive four tickets to a 2019 regular season NFL game and a $1,000 NFLShop.com gift card.

2019 Big Data Bowl Winners

College Entry

2019 Big Data Bowl Finalists

College Entry

Matthew Reyers, Dani Chu, Lucas Wu, James Thomson, Simon Fraser University – Routes to Success

• The group modeled play success rate and expected points under various passing route combinations. Using a technique called model-based clustering, the group found several complementary pass route patterns that could consistently yield positive outcomes, even when accounting for defensive formation and behavior.
• Key Stat: Through effective pass route combinations, an offense could control roughly 70% of the field.

OPEN ENTRY

Nathan Sterken – RouteNet: a convolutional neural network for classifying routes

• Sterken treated receiver routes as an image recognition problem, using a neural network to categorize each route. Once grouped, these patterns were compared to win probability added (the change in the offensive team’s chance of winning the game before and after the play).
• Key Stat: The flat-in-post route, a staple of the Steve Spurrier days at the University of Florida, was the best three-receiver route combination.

Finalists: 

• Kyle Burris, Duke University – A trajectory planning algorithm for quantifying space ownership in professional football
• Matthew Reyers, Dani Chu, Lucas Wu, James Thomson, Simon Fraser University – Routes to Success
• Jack Soslow, Jake Flancer, Eric Dong, Andrew Castle, University of Pennsylvania – Using autoencoded receiver routes to optimize yardage
• Peter Wu, Brendon Gu, Carnegie Mellon University – DIRECT: A two-level system for defensive interference rooted in repeatability, enforceability, clarity, and transparency 

Honorable mention: 

• Charles Gelman, Duke University – Identifying best receiver-route combinations
• Mitch Kinney, University of Minnesota – Untitled
• Dylan Blechner, Zak Koeppel, Will Friedeman, Cameron Johnson, Syracuse University – Route clustering
• Ali Kozlu, University of Pennsylvania – A framework for identifying route concepts using route trajectory data
• Zach Start, Brandon Deflon, University of New Mexico – Q-Sep: The NFL’s Metric for Quantifying Route Quantity

OPEN ENTRY

Finalists: 

• Sameer Deshpande, Katherine Evans – Expected hypothetical completion probability
• Cathy Ha, Lucas Calestini – Efficient speed usage and the impact of fatigue in speed performance: an exploratory study
• Nathan Sterken – RouteNet: a convolutional neural network for classifying routes
• Adam Vonder Haar – Exploratory data analysis of passing plays using NFL tracking data

Honorable mention: 

• Kyle Douglas, William Haynes, Momim Ghaffar, Farzad Vafaee – Missed extra punts
• Jesse Fischer – Identifying best receiver-route combinations
• Jacques Kvam and Karl Pazdernik – Receiver-route combinations that maximize separation
• Jason Phelps – Proof of concept for a receiver separation model using long short-term memory recurrent neural networks on Next Gen Player Tracking Data
• Kevin Zatloukal and Ben Gretch – Unusual effectiveness of crossing routes

2019 Finalists

College Entry

Kyle Burris, Duke University – A trajectory planning algorithm for quantifying space ownership in professional football

• Burris used metrics like player speed, direction and acceleration to chart the space occupied by the 22 players on the field. One example highlighted a 64-yard touchdown pass from Derek Carr to Johnny Holton to show how Holton’s speed and direction indicated that he was moving towards an open space well before he looked open on the field.

• Key Stat: In the play above, Carr released the pass only 0.3 seconds after Holton beat his defender, suggesting the quarterback knew he was going to Holton before the receiver broke free.

Peter Wu, Brendon Gu, Carnegie Mellon University – DIRECT: A two-level system for defensive interference rooted in repeatability, enforceability, clarity, and transparency

• Wu and Gu merged statistical modeling techniques with potential changes in penalty calls and receiver catch probability to consider new standards for defensive pass interference and defensive holding.
• Key Stat: There appear to be two peaks in catch probabilities on pass interference calls, about 55% and 75%, which suggests the feasibility of a two-level foul system.

Jack Soslow, Jake Flancer, Eric Dong, Andrew Castle, University of Pennsylvania – Using autoencoded receiver routes to optimize yardage

• The group presented three unique ways to represent pass route data, including time series and shape-based clustering. Merging in-play and game-specific traits, the group suggested that hitch routes are generally an underused strategy for increasing efficiency.
• Key Stat: Roughly one in three Odell Beckham pass routes was classified as a 10-yard curl pattern.

OPEN ENTRY

Sameer Deshpande, Katherine Evans – Expected hypothetical completion probability

• Deshpande and Evans tracked receiver catch probability across entire pass routes. Their approach allows for an estimation of the receiver’s performance regardless of when and where the pass was thrown.
• Key Stat: On an 18-yard touchdown pass to Cooper Kupp during Week 1 of the 2017 season, Rams quarterback Jared Goff had another receiver that was more open than Kupp. Roughly 1.5 seconds into his drop-back, had Goff thrown to Robert Woods, the pass would have had a 92% catch probability.

Cathy Ha, Lucas Calestini – Efficient speed usage and the impact of fatigue in speed performance: an exploratory study

• Ha and Calestini looked at the link between play specific factors such as play type, game factors (home vs. away, game surface, weather), and player fatigue (rest since last play, intensity of last play) and their impact on player speed efficiency.
• Key Stat: Alvin Kamara had the highest speed efficiency of any ball carrier during the first 6 weeks of the 2017 season.

Adam Vonder Haar – Exploratory data analysis of passing plays using NFL tracking data

• Vonder Haar classified routes and defensive space allocation to identify which route combinations yielded the most open receivers. His approach using convex hulls to characterize defender spacing was particularly novel.
• Key Stat: The receiver generating the highest maximum separation was only targeted on about one in five plays in the first six weeks of the 2017 season.

How the Contest Works

Here’s how you or your team can get involved:

1. Complete the below Registration Form

Eligible entrants may complete as an individual or a group (of 4 members or less) and must agree to the official rules.

2. Get the data

Once you complete and submit the registration form, keep an eye out for an email with instructions on how to access the raw data and next steps. You should receive this email moments after you submit your entry..

3. Dive into the themes

The three themes for the Big Data Bowl focus on respecting tradition, while embracing evolution. Participants may only submit for one theme.

4. Deliver your report

Eligible entrants must complete and submit the registration form below, as well as their report, by Jan. 22, 2019 at 11:59 PM ET to be eligible. More details will be provided in the email instructions after you complete the registration form.

5. Present your findings

NFL staff and club analytic personnel will determine the eight (8) Finalist Prize winners who will advance to the final presentation period in Indianapolis, IN. The Finalist Prize winners will present to a live audience and club staff while at the NFL Combine.