Champions have been crowned for the 2023 NFL Big Data Bowl on Kaggle
The University of Toronto's Hassaan Inayatali, Aaron White, and Daniel Hocevar have been named the winners with Between the Lines: How Do We Measure Pressure?
NFLDB 15% OFF
Includes 2023 NFL Draft Bible PDF copy and online historical library access


Powered by Amazon Web Services (AWS), the Big Data Bowl challenges members of the football analytics community - from college students to professionals - to analyze and rethink trends and player performance using traditional football data and Next Gen Stats. The competition aims to drive innovation and advance the way football is played and coached by engaging and empowering the analytics community. Through data and technology, the crowd-sourced competition encourages the creation of new insights, making the game more exciting for fans and protecting players from unnecessary risks. The 2023 Big Data Bowl culminated with an in-person event at the Scouting Combine in Indianapolis on March 1, where the winners were announced.
Congratulations to the 2023 Big Data Bowl Champions!
Hassaan Inayatali, Aaron White, Daniel Hocevar; University of Toronto
The team won the contest with their improved statistical model that transforms data derived from motion-tracking chips embedded in the players’ uniforms into animated heat maps.
The colourful visualizations provide real-time analysis of the pocket of space around the quarterback, including the amount of pressure he is under at any given moment and how long it is likely to last.Â
To read the Big Data Bowl champion’s full Kaggle project notes click here
Between the Lines: How Do We Measure Pressure?
How is this innovative and useful to the NFL?
Novel metrics such as Continuous Pocket Pressure (CPP), Offensive Pocket Life Expectancy (OPLE), Defensive Pocket Life Expectancy (DPLE), and Surplus Pressure (SP) allow us to evaluate offensive lines, defensive lines, and individual defensive linemen in their ability to resist/create pressure
CPP allows for the creation of different metrics to evaluate QB performance under varying levels of pressure, examine the distribution of passes at different pressure levels, optimize pass coverage for pressure while minimizing receiver separation, and analyze various game strategies and their impact on CPP
Visualization of CPP Data at each frame can be used for post-play analysis, in-game feedback, and TV Broadcasts
Introduction:
How do we measure pressure? While NFL statistics such as sacks, hurries, hits, and pressure rate allow us to understand the results of passing plays, they provide little information on the influence of defensive pass rushers on a quarterback (QB) over the duration of the play. Furthermore, attributing these statistics to the offensive line, defensive line, and QB is only possible through extensive play-by-play analysis which does not allow for a holistic evaluation of these units. The purpose of our NFL Big Data Bowl project is to better quantify the pressure a QB faces using player tracking data, isolate the performance of offensive/defensive lines from that of the QB, and determine the surplus pressure a defensive lineman provides relative to that of their teammates.
Focusing on plays in shotgun and empty formation:
We construct a Continuous Pocket Pressure (CPP) metric to determine the pressure a QB is under at every frame throughout a passing play, scaled from 0-100%. While the scope of our project is to quantify the performance of offensive/defensive lines, the applications of this metric extend to the evaluation of QBs and their ability to complete passes under varying levels of pressure, analyze the performance of different pass coverages at specific pressure levels, and determine which strategies (e.g. Hurry-Up Offence) lead to higher or lower levels of pressure.
With our CPP data, we apply survival analysis to develop two new metrics, Offensive and Defensive Pocket Life Expectancy (OPLE/DPLE) for every team in the NFL. With this result, we can determine which teams are best at resisting pressure as well as incurring pressure on a quarterback. Our methodology aims to isolate the impacts of offensive/defensive linemen in their ability to protect the QB.
We create a Surplus Pressure (SP) metric to evaluate the additional pressure a single defensive lineman provides relative to other players on the same team. We determine the DPLE for a team while the defensive lineman is on the field versus off to determine the surplus value a player provides relative to their teammates.
Read more at the Toronto Sun
Read more at U of T Engineering
Read more at U of T News
Look out for these new metrics coming from the broadcast booth as NFL and analytics are only getting more popular in the mainstream.
The 2023 Big Data Bowl Finalists
Coaching Track Finalists:
Undergrad Track Finalists:
Metric Track Finalists:
Honorable Mention:
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
Each year, the NFL Big Data Bowl calls on professional and aspiring amateur data scientists to devise innovative approaches to a specific challenge. Participants propose statistical, data-driven solutions using real-time data across a wide variety of players, plays and situations.
The call for participants typically is in the fall and the competition runs into early January. Entrants compete in two groups — College, featuring undergraduate and graduate students and Open, featuring young professionals not in higher education. Participants can work independently or form teams with other colleagues.
NFL club analytics staff judge each submission and work with NFL Football Operations staff to narrow down the finalists. Finalists then present their entry at the NFL Scouting Combine in Indianapolis to a panel of judges. In recent years, judges have included NFL Network predictive analytics expert, Cynthia Frelund, former Big Data Bowl participants, AWS data scientists and NFL linebacker Najee Goode.
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.
Have a great Saturday,
Ric
Purchase the 2023 NFL Draft Guide
All Acess Football Membership includes a PDF copy of the NFLDB.
Socialize with the Draftnick’s and ask Ric and Mike any questions you want on Private Zoom meets!
Access code will be provided in the NFLDB members area and emailed to all paid members for Private Zoom.
Online access to NFLDB historical archives
250 Limited Edition 2023 NFL Draft Bible hard copy + PDF download editions
Online access to the most accurate big board over the past two decades featuring projections for 2023 and beyond
In-depth scouting report library with thousands of prospect profiles for past, present and future
Verified player measureables, personal background information, medical history and historical stats
Dedicated, year-round coverage with on-site campus visits across the country
On location reporting from the all-star circuit, combine, pro days and draft
NFL Draft Substack Insider newsletter delivered directly to your inbox
Access to events and private Q&A with Ric