SMU Data Science Review
Abstract
American Football is a billion-dollar industry in the United States. The analytical aspect of the sport is an ever-growing domain, with open-source competitions like the NFL Big Data Bowl accelerating this growth. With the amount of player movement during each play, tracking data can prove valuable in many areas of football analytics. While concussion detection, catch recognition, and completion percentage prediction are all existing use cases for this data, player-specific movement attributes, such as speed and agility, may be helpful in predicting play success. This research calculates player-specific speed and agility attributes from tracking data and supplements them with descriptive factors to produce a quality data set that, with machine learning models, can lead to accurate predictions of success on a play-by-play basis. A neural network was trained to predict play success with an F1 score of 40%. Therefore, the true effect of the inclusion of player movement attributes in predicting play success appears to have a minimal effect, but additional data and future research may be needed to confirm that.
Recommended Citation
Horn, Hayley; Laigaie, Eric; Lopez, Alexander; and Reddy, Shravan
(2023)
"Using Geographic Information to Explore Player-Specific Movement and its Effects on Play Success in the NFL,"
SMU Data Science Review: Vol. 7:
No.
2, Article 3.
Available at:
https://scholar.smu.edu/datasciencereview/vol7/iss2/3
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Included in
Analysis Commons, Data Science Commons, Sports Studies Commons, Statistical Methodology Commons, Statistical Models Commons
