Wage Against the Machine: A Generalized Deep-Learning Market Test of Dataset Value

11 Pages Posted: 15 Dec 2015 Last revised: 12 Feb 2016

See all articles by Philip Maymin

Philip Maymin

Fairfield University - Charles F. Dolan School of Business

Date Written: December 14, 2015

Abstract

How can you tell if a particular sports dataset really adds value? The method introduced in this paper provides a way for any analyst in almost any sport to determine the additional value of almost any dataset.

Applying the method to NBA betting markets with a standard dataset available publicly as well as an augmented one incorporating data from Vantage Sports, we find that a rolling deep learning model with the augmented data substantially and significantly outperforms a similar machine learning model with the standard data over the 2014-2015 season. Furthermore, the performance with the augmented data is above the betting break even probability.

Finally, the same model without modification continues to outperform in subsequent markets and games, yielding a winning probability in excess of 56 percent for bets on games from the start of the season on October 27, 2015 through December 13, 2015.

Suggested Citation

Maymin, Philip, Wage Against the Machine: A Generalized Deep-Learning Market Test of Dataset Value (December 14, 2015). Available at SSRN: https://ssrn.com/abstract=2703636 or http://dx.doi.org/10.2139/ssrn.2703636

Philip Maymin (Contact Author)

Fairfield University - Charles F. Dolan School of Business ( email )

N. Benson Road
Fairfield, CT 06824
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
301
Abstract Views
1,297
rank
100,471
PlumX Metrics