Over 400 individuals participated in this year’s edition, a record high for the Big Data Bowl competition
New York, NY – The National Football League announced today the finalists for the fifth annual Big Data Bowl powered by Amazon Web Services (AWS). The annual sports analytics competition challenges contestants to 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. Each finalist receives $10,000 for being selected.
The theme of this year’s competition centered on offensive and defensive linemen. Participants received player tracking data from a sample of pass plays during the 2022 season to review pass block and pass rush strategies. PFF scouting data was also given to analyze offensive and defensive performances on both an individual and team basis. Using this data, each contestant was placed in one of three tracks: design a metric, coaching based, and undergraduate students. More than 400 data scientists from around the world participated in this year’s event – a Big Data Bowl record high – and the second-most all-time in a Kaggle analytics competition.
This year’s Big Data Bowl will conclude with an in-person event at the 2023 NFL Scouting Combine presented by NOBULL in Indianapolis on Wednesday, March 1. Eight contestants will be competing for an additional $20,000 in prize money and will also have an opportunity to meet and interact with the estimated 250 analytics staffers, coaches, and front office personnel in attendance at the final event.
“Year in and year out, we continue to be amazed by the enthusiasm and expertise of Big Data Bowl participants,” said Michael Lopez, Senior Director of Football Data & Analytics, NFL. “Our competition continues to spearhead the analytics movement in sports.”
“The Big Data Bowl brings together some of the most talented, aspiring data scientists for an opportunity to transform how football is analyzed, played, coached, and experienced,” said Julie Souza, Head of Sports, AWS Professional Services. “I’m excited to represent AWS as a judge in this year’s competition and meet the next generation of innovators.”
Since 2017, the NFL has utilized AWS as its official cloud and ML provider for the NFL Next Gen Stats (NGS) platform to uncover deeper insights and expand the fan experience by offering a broader range of advanced statistics. The Big Data Bowl continues to pave the way for new player statistics that are shared with teams and in network telecasts. In previous years, the NFL’s Football Data & Analytics and Next Gen Stats teams have collaborated on Big Data Bowl themes to develop metrics including expected rush yards, defensive coverage schemes, and expected punt return yards.
Each year, the Big Data Bowl continues to be the best opportunity for future data scientists to start a career in the sports industry. Over 50 past participants went on to a job in professional sports analytics, with more than 30 of those contestants hired by NFL clubs or player tracking vendors.
For the fourth year in a row, the Big Data Bowl has featured a mentoring program. Sixteen different mentees were paired with experienced NFL analytics experts and selected to join a four-month program that included analytics support and networking opportunities.
Below are the eight Big Data Bowl finalists for 2023, as well as nine honorable mention candidates, along with links to their submissions.
Coaching Track Finalists:
- Dominic Borsani, https://www.kaggle.com/code/dominicborsani/using-data-to-determine-blitz-strategy
- Joseph Ferraiola, Rohit Kumar, Ajay Patel & Cody Alexander, https://www.kaggle.com/code/josephferraiola/xpassrush-identifying-pass-rushers-pre-snap
Undergrad Track Finalists:
- Hassan Inayatali, Aaron White & Daniel Hocevar, University of Toronto, https://www.kaggle.com/code/hassaaninayatali/between-the-lines-how-do-we-measure-pressure
- Jay Sagrolikar & Paul Ibrahim, University of Chicago, https://www.kaggle.com/code/jaysagrolikar/open-space-spatial-survival-probabilities/notebook
Metric Track Finalists:
- Gregory J Matthews & Quang Nguyen, https://www.kaggle.com/code/statsinthewild/strain-sacks-tackles-rushing-aggression-index
- Nick Bachelder, https://www.kaggle.com/code/nickb1125/idpi-a-situational-metric-for-pass-rushers
- Sho Sekine & Nao Sekine, https://www.kaggle.com/code/lichtlab/evaluate-linemen-using-player-impact-distribution
- Vincent Karpick, https://www.kaggle.com/code/vincentkarpick/completions-added-through-suppression-of-pressure
- Ian Astalosh, https://www.kaggle.com/code/ianasta23/coerce-a-measure-of-early-pass-rush-pressure
- Michael Egle & Kenan Clake, https://www.kaggle.com/code/michaelegle/good-rush-bad-blocking
- Avery Elizabeth Horvath, https://www.kaggle.com/code/averyehorvath/pass-rush-predictor-for-blocking-assignments
- Ben Jenkins & Steve Jenkins, https://www.kaggle.com/code/benjenkins96/causal-impact-of-offensive-linemen-on-pass-plays
- Samuel Kirschner, https://www.kaggle.com/code/slayerpark/pop-deacon-pressure-impact-on-completion
- Morgan Martin, Drew Beamer & Richard Noe, Davidson College, https://www.kaggle.com/code/morganmartin23/nfl-data-bowl-2023-initial-pass-set-kick-speed
- Tej Seth, Joey DiCresce & Arjun Menon, University of Michigan, https://www.kaggle.com/code/tejseth/hack-a-sack/
- Charlie Singer, University of California Berkeley, https://www.kaggle.com/code/charliesinger/the-shield
- Lau Sze Yui, https://www.kaggle.com/code/s903124/evaluate-pass-block-with-graphical-neural-network