Abstract

American Football has risen to new levels of popularity in America. At the pinnacle of the industry is the NFL. The NFL is not only extremely popular, but very lucrative. One of the biggest aspects of the NFL today, is Fantasy Football. Websites like FandDuel and DraftKings have millions of players each week betting on which players will perform best and, in states where it's legal, fans can gamble on which teams will make the playoffs and win games. In this project we provide a deep exploration into finding a model that can accurately predict which NFL teams will make the playoffs, using only statistics from each team. We explain which statistics are most important in predicting well-performing teams from a professional opinion, and from data analysis. We investigate these statistics using analytics and machine learning to both model and analyze past data. The main goals of the investigation are to gain a better understanding of what statistics, machine learning model, and methods most accurately predict which NFL teams will make the playoffs. Through the investigation, we present our findings on the impact of past statistics and against other models.

Advisor

Byrnes, Denise

Department

Computer Science

Disciplines

Artificial Intelligence and Robotics

Keywords

Machine Learning, Artificial Intelligence, Decision Trees, Principal Component Analysis, Predictive Models

Publication Date

2020

Degree Granted

Bachelor of Arts

Document Type

Senior Independent Study Thesis

Download

Share

COinS
 

© Copyright 2020 Robert Alvarez