Graduate Students
Graduate Programs     
Graduate Home Ph D Programs Masters Degree Ph D Program Requirements Course Descriptions Current Courses Admissions Current Graduate Students Graduate Student Seminar SIAM Chapter Seminar Recent Graduates Incoming Students

Apply Now
Graduate Seminar

Samuel Ventura
Carnegie Mellon University
Title: Modern Football Analytics

Abstract: American football is an extremely complicated sport. With so many rules and unique situations, it can take a lifetime for the average fan to fully understand some of the complexities involved in the game, especially with respect to on-field decision-making. In this talk, I will give a brief overview of how American football is played, before providing a detailed overview of how data analysis and modern statistical methods can be used in many parts of a modern football game. I will focus on two core concepts, which have been described as "the holy grail" of modern football analytics: expected points and win probability. I will also detail how statistical models can be used to improve player evaluation for both the NFL draft and NFL free agency. I will discuss how interested researchers can obtain football data for their own analyses, and how this relates to some ongoing research (on campus!) I have in the Statistics Department. Finally, I will discuss the use of RFID (Radio Frequency IDentification) technology in the NFL, and what we questions we might be able to answer with the resulting datasets.

For those unfamiliar with American football, I recommend reading this "Football 101" article (or something similar) before my talk: http://thefootballgirl.com/football-101/nfl-rules.html

Date: Tuesday, February 2, 2016
Time: 5:30 pm
Location: Wean Hall 8220
Submitted by:  Yangxi Ou
Note: Video on Youtube: https://youtu.be/dEGTe0TCwgQ