AUTHOR=Schmid Marc , Blauberger Patrick , Lames Martin 

TITLE=Simulating Defensive Trajectories in American Football for Predicting League Average Defensive Movements

JOURNAL=Frontiers in Sports and Active Living

VOLUME=Volume 3 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/sports-and-active-living/articles/10.3389/fspor.2021.669845

DOI=10.3389/fspor.2021.669845

ISSN=2624-9367

ABSTRACT=This study proposes a data driven ghosting approach in American football. Deep neural networks are trained with a multi agent imitation learning approach, using players' tracking data of a whole NFL regular season. This approach introduces a method to evaluate defensive trajectories, by comparing the movements of individual plays to simulated league average behavior.
To evaluate the quality of the predicted movements, a formation based pass completion probability model is introduced. With the implementation of a learnable order invariant model, based on insights of molecular dynamical machine learning, the accuracy of the model is increased to 81\%. The trained pass completion probability model is used to evaluate the ghosted trajectories and serves as a metric to compare the true trajectory to the ghosted ones.
Additionally, the study evaluates the ghosting approach with respect to different optimization methods and dataset augmentation. It is shown that a multi agent imitation learning approach, trained with a dataset aggregation method outperforms vanilla approaches on the dataset. This network and evaluation scheme presents a new method for teams, sports analysts and sport scientists to evaluate defensive plays in American football and  lays the foundation for more sophisticated data driven simulation methods.