ORCID Identifier(s)

0000-0002-2583-2597

Graduation Semester and Year

2017

Language

English

Document Type

Thesis

Degree Name

Master of Science in Industrial Engineering

Department

Industrial and Manufacturing Systems Engineering

First Advisor

Kim Aera LeBoulluec

Abstract

In the new age of daily fantasy sports (DFS), fantasy football has become an enormous revenue generator for DFS sites, such as DraftKings and FanDuel. Both companies are valued over \$1 billion. However, previous analysis done by popular DFS site Rotogrinders has shown that only the top players are consistently winning, the top 10 players much more frequently than the remaining 20,000 players. Using complex statistical models they're able to identify top athletes and value picks (based on an athlete's draft `salary') that the average player might not be aware of. There is a need to evaluate which methods and algorithms are best at predicting fantasy football point output. These methods could then be applied to future DFS contests outside of football to see if they predict other fantasy sports point output well. There are few resources and little literature available on this subject. Several factors contribute. Daily Fantasy Sports are still relatively new, and many people are still just starting to get involved in them. Also, very few people have published their work on their custom models or significant variables, since they are generally developing these models for personal use in an attempt to gain an edge in DFS contests and win money. Thus, there is little to no motivation to make their research or methods publicly available. This research will attempt to predict the weekly point output of a quarterback based on a variety of attributes and metrics. Finding the important variables and statistical models and learning how to address the volatility in week-to-week performances for a quarterback will allow us to expand this to other player positions in the future. In addition to understanding the best algorithms to apply to weekly point prediction and the best variables to use to predict a quarterback's output, this research also seeks to answer the question that is a currently being debated in courtrooms across the country - should DFS be considered a legal game of skill, or a game of luck, and therefore online gambling?

Keywords

Data mining, Predictive analytics, Data science, Daily fantasy football, DraftKings, Regression

Disciplines

Engineering | Operations Research, Systems Engineering and Industrial Engineering

Comments

Degree granted by The University of Texas at Arlington

26766-2.zip (2308 kB)

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.