Date of Defense

3-17-2025

Date of Graduation

4-2025

Department

Business Information Systems

First Advisor

Carrie Song

Second Advisor

Yingying Zhang

Abstract

In this thesis I examined the use of AI modeling for the use in the modern-day NFL, both for improving in-game play calling, and creating better recovery plans for players all around the league. When finding articles detailing these models, I only focused on works involving the current day NFL, and models used widely around the league to this day. The literature detailed in this thesis mainly describes modeling used by Amazon Web Services (AWS, 2024, The NFL’s partner for all things analytics, and data modeling. My main objective for this literature review was to show the impact AI modeling has for the future of the NFL, and what model is specifically best for the best results to be achieved for the safety and Improvement of the modern NFL game. There are numerous different kinds of AI models that can be used for data modeling, such as Deep Learning Models, Decision Trees, Generative AI models, and much more. All of these models have unique abilities and drawbacks, which this review will compare to show which is best for the NFL to use. Being a football aficionado and Computer Information Systems major myself, this use of Artificial intelligence in the NFL has intrigued me greatly, and I want to know how these models are being used to make the game better, and more exciting. In the past, pro football has been hindered by player injuries, mainly doubts as to how players are getting hurt, and noticing any trends in the process. By using AI, the NFL can be benefited greatly as injury data can be gathered and analyzed, to get a better understanding of any trends/patterns that are getting players hurt, so rules can be amended and revised to keep players safe in a game as violent and demanding as pro football. Not only can AI modeling assist with player safety but also can provide insights to coaches regarding game situations and play calling, to help them make better in-game decisions to benefit their team and make the game more exciting. For instance, if a coach is torn on whether or not to go for it on fourth down or kick a field goal, these coaches can reference data from past scenarios such as this, and through AI predictive modeling can make a better informed decision based on these numbers, which can potentially win them more games and make games more exciting than ever before. As the NFL’s viewership continues to soar, AI modeling will attract more players to the sport, and make fans drawn to the sights and sounds of the game like never before.

Access Setting

Honors Thesis-Open Access

Additional Files
Honors Thesis Presentation McManus.pdf (270 kB)
Defense Presentation
Download

Share

COinS