Dissertation/Thesis Abstract

Using Machine Learning Methods to Predict NFL Victors
by Urista Benitez, Octavio Misael, M.S., California State University, Long Beach, 2017, 88; 10606129
Abstract (Summary)

In this thesis, we predict end-of-game results for National Football League regular season games after week 6 (not including playoffs) using machine learning methods. The features we use in our analysis are readily available to the public. Most of the features will be in-game statistics, such as passing yards and rushing yards. The out-of-game statistics we use include win percentage and average team scores (for both sides). Methods include logistic regression, k-nearest neighbors, random forest, and support vector machine. In addition, a combined model is created. The accuracy, sensitivity, and specificity of our models is compared to the accuracy, sensitivity, and specificity of the point spread.

Indexing (document details)
Advisor: Suaray, Kagba
Commitee: Korosteleva, Olga, Safer, Alan
School: California State University, Long Beach
Department: Mathematics and Statistics
School Location: United States -- California
Source: MAI 57/01M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Statistics, Artificial intelligence
Keywords:
Publication Number: 10606129
ISBN: 9780355318623
Copyright © 2019 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest