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

Abstract

American football is an appealing field of research for the use of information technology. While much effort is made to analyze the offensive team in recent years, reasoning about defensive behavior is an emergent topic. As defensive performance and positioning largely contribute to the overall success of the whole team, this study introduces a method to simulate defensive trajectories. The simulation is evaluated by comparing the movements in individual plays to a simulated league average behavior. A data-driven ghosting approach is proposed. Deep neural networks are trained with a multi-agent imitation learning approach, using the tracking data of players of a whole National Football League (NFL) regular season. 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 baseline approaches on the dataset. This network and evaluation scheme presents a new method for teams, sports analysts, and sports scientists to evaluate defensive plays in American football and lays the foundation for more sophisticated data-driven simulation methods.

Tactics analysis and evaluation of women football team based on convolutional neural network

“…CNN is one of the most important networks in the field of deep learning, and has made impressive achievements in many fields 21 . CNN, including but not limited to computer vision and natural language processing, can be used in multiple scenes 22 , 23 .…”

Developing a High-Performance Sports Results Prediction Artificial Neural Network: Case Study on World Championship Boxing

“…✮✱✮✰✶ ✱✻ ✡ ✭✮✁✲✩✬✭ ✁ ✡☞☛ ✩✪✹✶✁✲✬✲ ✴✬✳✬ ✱✻ ✆✯✱✱✲✝ ☎✬✮✄✱✲✱✶✱✯✩✹✰✶ ✄✁✰✶✩✮✺✂ ✟✬✪ ✭✮✁✲✩✬✭ ✴✬✳✬ ✹✶✰✭✭✩✻✩✬✲ ✰✭ ✆✻✰✩✳✝ ☎✬✮✄✱✲✱✶✱✯✩✹✰✶ ✄✁✰✶✩✮✺ ✁✂✂☞☛ ✰✪✲ ✮✴✱ ✭✮✁✲✩✬✭ ✴✬✳✬ ✱✻ ✆✸✱✱✳✝ ☎✬✮✄✱✲✱✶✱✯✩✹✰✶ quality (3%) as these studies did not specify the participants included in the study, they did not include a valid or reliable injury surveillance or quantification of training/ match load (Schmid et al 2021;Shim et al 2020).…”

Player Tracking Data in Sports

“…Felsen et al (2018) developed a conditional variational autoencoder architecture for the prediction of player movement in basketball, while Alcorn & Nguyen (2021) developed a multientity transformer for the same objective. Deep imitation learning (IL) has been applied to the prediction of defensive movement trajectories in soccer (Le et al 2017a) and American football (Schmid et al 2021).…”

“…These authors developed an IL strategy that uses LSTM to describe role-specific player trajectories and a multiphase training approach that iteratively switches between evaluations of the policies of individual players and the collective policy of a team. The multiagent methodology originally developed for tactical optimization in soccer has also been applied to basketball (Seidl et al 2018) and American football (Schmid et al 2021).…”