Corpus ID: 1060968

Predicting Offensive Play Types in the National Football League

  title={Predicting Offensive Play Types in the National Football League},
  author={Peter Lee and Ryan Chen and V. Lakshman},
In this paper, we apply tools from machine learning to the burgeoning field of football analytics and predict whether a team will run or pass the ball on a given play. After training four different classification algorithms on data from the 2012-2014 NFL seasons, we developed an ensemble method that combines the predictions of our two best-performing individual models and achieved a test accuracy of 75.9%, improving upon previously published results. We also explored general trends in offensive… Expand
4 Citations

Tables from this paper

Predicting plays in the National Football League
An interpretable machine learning model to predict plays (pass versus rush) in the National Football League that will be useful for players and coaches in real time is developed. Expand
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 variety of sports to gain an advantage by, e.g., analysing potential strategies of opponents. Whereas the availability ofExpand
Using K-means Clustering to Create Training Groups for Elite American Football Student-athletes Based on Game Demands
Background: American football and the athletes that participate have continually evolved since the sport’s inception. The fluidity of the sport, as well as the growth of the body of knowledgeExpand


An empirically driven mathematical modelling analysis for play calling strategy in American football
The analysis utilises a game‐theoretic approach embedded within a stochastic dynamic programming formulation, resulting in a mixed strategy satisfying the ex‐ante declared objective of maximising the probability of scoring a touchdown. Expand
Optimizing Football Game Play Calling
Play calling strategies during football games are extremely important to the success of a team. In the past, coaches and players have subjectively determined the plays to call based on pastExpand
Scikit-learn: Machine Learning in Python
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringingExpand
Assessing the Predictability of an NFL Offense
  • MIT Sloan Sports Analytics Conference,
  • 2016
NFL play predictions
  • JSM Proceedings, Statistical Computing Section,
  • 2015
Optimal strategies on fourth down
  • Management Science,
  • 1978