TRAP@NCI

Man v Machine: Greyhound Racing Predictions

Lyons, Alva (2016) Man v Machine: Greyhound Racing Predictions. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (2MB) | Preview

Abstract

The purpose of this research is to ascertain whether greyhound racing results can be predicted with a high degree of certainty using machine learning techniques. The main focus of this research is in bridging the gap between existing sports prediction models which use manual feature selection to creating a model built from machine chosen subsets by algorithmically sub-setting the feature space. Feature selection is the process of sub setting the feature space by analysing the relevance of features both to each other and to the predicted variable so that only the most relevant features are used within the modelling framework. The reason for introducing the greyhound expert is to test whether the model can outperform the average social gambler who tend to make their betting selection based on tips given to them by domain experts.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 27 Jan 2017 17:22
Last Modified: 27 Jan 2017 17:22
URI: http://trap.ncirl.ie/id/eprint/2527

Actions (login required)

View Item View Item