Date of Award

5-2020

Document Type

Master's Project

Degree Name

Master of Science (MS)

College/School

College of Science and Mathematics

Department/Program

Computer Science

Thesis Sponsor/Dissertation Chair/Project Chair

Vaibhav K. Anu

Committee Member

Aparna S. Varde

Committee Member

Dawei Li

Abstract

[Background] Daily fantasy sports (DFS) are a variety of fantasy sports where contests take place in a matter of days or hours rather than over a whole season. A disparity exists between skilled professionals and casual participants in the creation of line-ups (i.e. teams) w.r.t their chances of winning in these contests. The purpose of the current project was to create a user-friendly, open source platform (named DFL-Opt) for participants of all skill levels to utilize in the creation of DFS line-ups. In addition, efficacy of the DFL-Opt platform was determined by playing the lineups generated by the DFL-Opt tool in real contests on the website, DraftKings.

[Method] The platform was developed using an optimization approach based on linear programming. Comparison of results was performed based on five contests involving DraftKings Showdown Captain Mode between February 24th, 2020 through March 2nd, 2020.

[Result] DFL-Opt generated lineups place in the top 95 percentile in three out of the five contests that were played. The remaining results were compromised by factors such as player injuries (such factors are currently not included in the scope of the DFL-Opt platform and are part of future work).

[Conclusion] Based on the results, this approach used by DFL-Opt tool is an effective strategy to create competitive line-ups in DFS contests regardless of level of professionalism/skills of contestants.

Comments

This report was submitted by Francis Aurori in partial fulfillment of the requirements for the degree of Master of Science in Computer Science. This report was submitted to the Department of Computer Science, Montclair State University.

File Format

PDF

Download

Share

COinS