Papers

NFL Ghosts: A framework for evaluating defender positioning with conditional density estimation

football
player-tracking data
random forests
conditional density estimation
ghosting
Big Data Bowl
expected points
A ghosting framework to evaluate players with high-dimensional tracking data features through distribution estimates via flexible random forests for conditional density estimation.
Jun 25, 2024
Ronald Yurko, Quang Nguyen, Konstantinos Pelechrinis

Fractional tackles: Leveraging player tracking data for within-play tackling evaluation in american football

football
Big Data Bowl
player-tracking data
Introducing fractional tackles, a new way to measure tackles with player-tracking data (2024 Big Data Bowl finalist)
Mar 21, 2024
Quang Nguyen, Ruitong (Larry) Jiang, Meg Ellingwood, Ronald Yurko

Here Comes the STRAIN: Analyzing Defensive Pass Rush in American Football with Player Tracking Data

football
Big Data Bowl
player-tracking data
multilevel models
Introducing STRAIN, a novel metric for measuring pass rushers (2023 Big Data Bowl finalist)
Jul 25, 2023
Quang Nguyen, Ronald Yurko, Gregory J. Matthews

Augmenting adjusted plus-minus in soccer with FIFA ratings

player ratings
soccer
adjusted plus-minus
Bayesian
Introducing augmenting adjusted plus-minus, which combines external rating systems (FIFA ratings) with adjusted plus-minus to improve player ratings
Feb 22, 2023
Francesca Matano, Lee F. Richardson, Taylor Pospisil, Collin A. Politsch, Jining Qin

Filling the Gaps: A Multiple Imputation Approach to Estimating Aging Curves in Baseball

aging curves
baseball
multiple imputation
survival bias
Studying the baseball aging curves in a missing data context and account for different types of dropouts of baseball players during their careers
Jan 29, 2023
Quang Nguyen, Gregory J. Matthews

Big ideas in sports analytics and statistical tools for their investigation

datasets
pairwise comparisons
R packages
sports analytics
sports data
Highlighting big ideas in sports analytics by defining the concepts mathematically, explaining how they originated, and giving examples of their applications in multiple sports
Jan 10, 2023
Benjamin S. Baumer, Gregory J. Matthews, Quang Nguyen

Opening up the court: analyzing player performance across tennis Grand Slams

tennis
hierarchical models
mixed-effects models
This paper explores differences among Grand Slams, while adjusting for confounders such as tour, competitor strength, and player attributes for matches from 2013 to 2019
Jul 7, 2021
Shannon K. Gallagher, Kayla Frisoli, Amanda Luby

TRAP: a predictive framework for the Assessment of Performance in Trail Running

trail running
random forests
prediction intervals
An introduction to modeling trail running performance
Sep 30, 2020
Riccardo Fogliato, Natalia L. Oliveira, Ronald Yurko

Unsupervised methods for identifying pass coverage among defensive backs with NFL player tracking data

football
player-tracking data
Big Data Bowl
mixture models
Using gaussian mixture models with NFL tracking data to identify man versus zone pass coverage
May 29, 2020
Rishav Dutta, Ronald Yurko, Samuel L. Ventura

Extracting NFL tracking data from images to evaluate quarterbacks and pass defenses

football
player-tracking data
completion probability
image extraction
generalized additive models
How Sarah Mallepalle created next-gen-scraPy and became an NFL inspiration
Apr 28, 2020
Sarah Mallepalle, Ronald Yurko, Konstantinos Pelechrinis, Samuel L. Ventura

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

football
player-tracking data
Big Data Bowl
expected points
win probability
continuous-time expected value
deep learning
conditional density estimation
An introduction to continuous-time, within-play expected value in football demonstrated with ball-carrier models
Jan 13, 2020
Ronald Yurko, Francesca Matano, Lee F. Richardson, Nicholas Granered, Taylor Pospisil, Konstantinos Pelechrinis, Samuel L. Ventura

nflWAR: a reproducible method for offensive player evaluation in football

football
expected points
win probability
player evaluation
multilevel models
An introduction to reproducible expected points, win probability, and player evaluation models in American football
Apr 16, 2019
Ronald Yurko, Samuel L. Ventura, Maksim Horowitz

Competing process hazard function models for player ratings in ice hockey

ice hockey
player ratings
Bayesian
hierarchical models
competing process models
Cox model
Modeling player ratings in ice hockey by treating the game as a competing stochastic process
Feb 28, 2013
A. C. Thomas, Samuel L. Ventura, Shane T. Jensen, Stephen Ma
No matching items