TRAP@NCI

Using Machine Learning to Predict the Winning Score of Professional Golf Events on the PGA Tour

Wiseman, Oisín (2016) Using Machine Learning to Predict the Winning Score of Professional Golf Events on the PGA Tour. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration File)
Download (1MB) | Preview

Abstract

Online sports betting is big business, particularly in play betting. It is a competitive market with bookmakers constantly looking for new types of bets to attract customers. Betting on the winning score of a golf event is not something offered by bookmakers today. In this paper linear regression and feature selection are applied to uncover a novel set of features that can predict the winning score of a golf event once the first round is complete. Various machine learning algorithms are evaluated using these features to determine which ones can accurately predict the winning score. Using Azure Machine Learning, applications are built to predict the winning score of an event based on data from the first round. This research would be of interest to online bookmakers looking to gain a competitive advantage by adding to their portfolio of in-play bets. In addition, the outcomes of this paper would be beneficial to golfers who could adjust their tactics during the event based on the predicted score. The final applications are validated against completed events on the 2016 PGA Tour. The machine learning models outperform the best known method of predicting the winning score in existence today by 50% for predictions within one shot of the final score. The Bayesian linear regression algorithm is the most accurate predicting the exact score in 22% of the events and 67% to within 3 shots of the winning score.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

G Geography. Anthropology. Recreation > GV Recreation Leisure > Games and Amusements > Gambling
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 03 Dec 2016 12:16
Last Modified: 03 Dec 2016 12:16
URI: http://trap.ncirl.ie/id/eprint/2493

Actions (login required)

View Item View Item