Punt Returns: Using the Math to Find the Best Path

Simon Fraser University Sports Analytics Group

Robyn Ritchie, PhD Student | Linkedin | Twitter: @RR_SportsStats

Brendan Kumagai, MSc Student | Linkedin | Twitter: @BrendanKumagai

Ryker Moreau, MSc Student | Linkedin | Twitter: @RMoreau18

Elijah Cavan, MSc Student | Linkedin | Twitter: @cavan_elijah

Submission for the 2022 NFL Big Data Bowl - Student Competition

This repository contains all code, figures, and citations used for our Big Data Bowl submission along with additional punt return optimal path visualizations as generated by the algorithm outlined in our paper.

Repository Directory

Code

Our code is divided into three folders:

1. Data Standardization: Our process of standardizing the data so that all punt returns are moving from left to right

2. Models: Our models for tackle probability and expected return yards.

3. Optimal Path: Our algorithm to determine the punt returner's optimal path given the defensive structure of the kicking team.

Figures from Paper

Figures from our paper can be found in the "Figures" folder.

Touchdown Plays from 2020

To view additional optimal path and convex hull animations for all 2020 touchdown plays, please see the "Optimal Path/Sample Plays" folder.

Acknowledgements

We would like to thank Dr. Tim Swartz, Dr. Tom Loughin, Dr. Alexandre Leblanc, and Tyrel Stokes for taking the time to provide guiance and feedback on our work. We would also like to thank Michael Lopez, the National Football League, and Pro Football Focus for graciously organizing this competition and providing such detailed and interesting data to work with.

Bibliography

Aronov, Boris, Sariel Har-Peled, Christian Knauer, Yusu Wang, and Carola Wenk. “Fréchet Distance for Curves, Revisited” in Algorithms - ESA 2006. Azar, Yossi; Erlebach, Thomas; Kittler, Josef. Springer Berlin / Heidelberg (2006). 52-63.

Guan, Tianyu, Jiguo Cao, and Tim B. Swartz. (2021) “Should You Park the Bus?” [submitted and under review]. Simon Fraser University. Downloaded Jan 5/22 at https://www.sfu.ca/~tswartz/.

Hart, Peter E, Nils J Nilsson, and Bertram Raphael. “A Formal Basis for the Heuristic Determination of Minimum Cost Paths.” IEEE transactions on systems science and cybernetics 4.2 (1968): 100–107. Web.

Kuhn, M. (2008). Building Predictive Models in R Using the caret Package. Journal of Statistical Software, 28(5): 1 - 26.

Lee, Der-Tsai, and Bruce J Schachter. “Two algorithms for constructing a delaunay triangulation.” International Journal of Computer & Information Sciences, 9(3): 219–242, 1980.

Pospisil, Taylor, and Ann B. Lee. "Rfcde: Random forests for conditional density estimation." arXiv preprint arXiv:1804.05753 (2018).

Rumsey, Deflon. (2020) “Quantifying Leverage at the Point of Attack” Big Data Bowl 2020

Yurko, Ronald, Francesca Matano, Lee Richardson, Nicholas Granered, Taylor Pospisil, Konstantinos Pelechrinis, and Samuel Ventura. “Going deep: models for continuous-time withinplay valuation of game outcomes in American football with tracking data. Journal of Quantitative Analysis in Sports 16, no. 2 (2020): 163-182