Submission Title

Beat the Spread: Predicting NFL Professional Football Results

Session Title

Session 1-3-C: Lightning Talks

Presentation Type

Lightning Talk

Location

Park MGM, Las Vegas, NV

Start Date

23-5-2023 1:45 PM

End Date

23-5-2023 3:15 PM

Disciplines

Artificial Intelligence and Robotics

Abstract

This lightning talk describes a machine learning system named "Zoltar" that predicts the results of NFL professional football games. The system uses deep neural technologies combined with classical information theory techniques. Over the past four seasons, the Zoltar system has scored 62.5% accuracy against the Las Vegas point spread.

Keywords

machine learning, sports, wagering

Author Bios

James McCaffrey works for Microsoft Research in Redmond, Wash. James has a PhD in cognitive psychology and computational statistics from the University of Southern California, a BA in psychology, a BA in applied mathematics, and an MS in computer science. James learned to speak to the public while working at Disneyland as a college student, and he can still recite the entire Jungle Cruise ride narration from memory.

Funding Sources

No relevant funding sources.

Competing Interests

No relevant competing interests.

Comments

This presentation is intended to be lightweight and mildly entertaining, and accessible to a broad audience, rather than a deeply technical research talk.

Share

COinS
 
May 23rd, 1:45 PM May 23rd, 3:15 PM

Beat the Spread: Predicting NFL Professional Football Results

Park MGM, Las Vegas, NV

This lightning talk describes a machine learning system named "Zoltar" that predicts the results of NFL professional football games. The system uses deep neural technologies combined with classical information theory techniques. Over the past four seasons, the Zoltar system has scored 62.5% accuracy against the Las Vegas point spread.