Simulation-Based Decision Making in the NFL using NFLSimulatoR

02/03/2021
by   Benjamin Williams, et al.
0

In this paper, we introduce an R software package for simulating plays and drives using play-by-play data from the National Football League. The simulations are generated by sampling play-by-play data from previous football seasons.The sampling procedure adds statistical rigor to any decisions or inferences arising from examining the simulations. We highlight that the package is particularly useful as a data-driven tool for evaluating potential in-game strategies or rule changes within the league. We demonstrate its utility by evaluating the oft-debated strategy of going for it on fourth down and investigating whether or not teams should pass more than the current standard.

READ FULL TEXT
03/24/2020

Predicting play calls in the National Football League using hidden Markov models

In recent years, data-driven approaches have become a popular tool in a ...
06/05/2019

Going Deep: Models for Continuous-TimeWithin-Play Valuation of Game Outcomesin American Football with Tracking Data

Continuous-time assessments of game outcomes in sports have become incre...
06/05/2019

Going Deep: Models for Continuous-Time Within-Play Valuation of Game Outcomes in American Football with Tracking Data

Continuous-time assessments of game outcomes in sports have become incre...
04/28/2020

Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners

Hanabi is a cooperative game that challenges exist-ing AI techniques due...
02/04/2014

Analysis of Watson's Strategies for Playing Jeopardy!

Major advances in Question Answering technology were needed for IBM Wats...
09/16/2019

BasketballGAN: Generating Basketball Play Simulation Through Sketching

We present a data-driven basketball set play simulation. Given an offens...
10/27/2019

Expected Hypothetical Completion Probability

Using high-resolution player tracking data made available by the Nationa...