Going deep: models for continuous-time within-play valuation of game outcomes in American football with tracking data

Yurko Ronald (), Matano Francesca (), Richardson Lee F. (), Granered Nicholas (), Pospisil Taylor (), Pelechrinis Konstantinos () and Ventura Samuel L. ()
Additional contact information
Yurko Ronald: Carnegie Mellon University, Statistics and Data Science, Pittsburgh, PA, USA
Matano Francesca: Carnegie Mellon University, Statistics and Data Science, Pittsburgh, PA, USA
Richardson Lee F.: Carnegie Mellon University, Statistics and Data Science, Pittsburgh, PA, USA
Granered Nicholas: University of Pittsburgh, Statistics, Pittsburgh, PA, USA
Pospisil Taylor: Carnegie Mellon University, Statistics and Data Science, Pittsburgh, PA, USA
Pelechrinis Konstantinos: University of Pittsburgh, School of Computing and Information, Pittsburgh, PA, USA
Ventura Samuel L.: Carnegie Mellon University, Statistics and Data Science, Pittsburgh, PA, USA

Journal of Quantitative Analysis in Sports, 2020, vol. 16, issue 2, 163-182

Abstract: Continuous-time assessments of game outcomes in sports have become increasingly common in the last decade. In American football, only discrete-time estimates of play value were possible, since the most advanced public football datasets were recorded at the play-by-play level. While measures such as expected points and win probability are useful for evaluating football plays and game situations, there has been no research into how these values change throughout the course of a play. In this work, we make two main contributions: First, we introduce a general framework for continuous-time within-play valuation in the National Football League using player-tracking data. Our modular framework incorporates several modular sub-models, to easily incorporate recent work involving player tracking data in football. Second, we use a long short-term memory recurrent neural network to construct a ball-carrier model to estimate how many yards the ball-carrier is expected to gain from their current position, conditional on the locations and trajectories of the ball-carrier, their teammates and opponents. Additionally, we demonstrate an extension with conditional density estimation so that the expectation of any measure of play value can be calculated in continuous-time, which was never before possible at such a granular level.

Keywords: expected points; football; player tracking data; recurrent neural networks; win probability (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://doi.org/10.1515/jqas-2019-0056 (text/html)
For access to full text, subscription to the journal or payment for the individual article is required.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bpj:jqsprt:v:16:y:2020:i:2:p:163-182:n:5

Ordering information: This journal article can be ordered from
https://www.degruyter.com/journal/key/jqas/html

DOI: 10.1515/jqas-2019-0056

Access Statistics for this article

Journal of Quantitative Analysis in Sports is currently edited by Mark Glickman

More articles in Journal of Quantitative Analysis in Sports from De Gruyter
Bibliographic data for series maintained by Peter Golla ().