Student Work

 

Performing Binary Classification of Contests Profitability for Draftkings Public

Downloadable Content

open in viewer

In this Major Qualifying Project, we worked alongside the online daily fantasy sports company DraftKings to build an algorithm that would predict which of the company's contests would be profitable for them. Our goal was to detect contests at risk of not filling to their maximum number of entrants by four hours before the contest closed. We combined categorical and numerical header data provided by DraftKings for hundreds of thousands of contests using modern data science techniques such as ensemble methods. We then utilized parameter estimation techniques to model the time series data of entrants into a given contest. Finally these parameters were fed into a Random Forest algorithm with the header data that provided our final prediction as to whether a contest would fill or not.

Creator
Publisher
Identifier
  • E-project-042419-131241
Advisor
Year
  • 2019
Sponsor
Date created
  • 2019-04-24
Resource type
Major
Rights statement
License

Relationships

In Collection:

Items

Permanent link to this page: https://digital.wpi.edu/show/pg15bh26d