TRAP@NCI

Analysis of Horse jump racing data and using predictive analytics to predict how many horses will fall in a race

Geraghty, Michael (2014) Analysis of Horse jump racing data and using predictive analytics to predict how many horses will fall in a race. Diploma thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Diploma)
Download (2MB) | Preview

Abstract

This paper examines the domain of Horse Jump racing and the application of predictive modelling to predict horses falling in a race. The historical race data comes from the sportinglife website and the paper details how to extract this race data and the most appropriate method to extract the data with research into API’s in this domain as well as examining programming as a data extraction method. A dataset of historical race data from the Aintree Grand National meeting is created. This data set is analysed through excel, R and Weka using advanced statistical techniques. A number of algorithms used for predictive analytics in a variety of sports are looked at and then the most appropriate to predict the outcome of a horse race dataset are then selected. These algorithms are applied to the dataset with the aim of predicting whether or not a horse falls in a race. A breakdown and comparison of the results is given to show which algorithm is best suited for such an analysis.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 15 Dec 2014 15:47
Last Modified: 15 Dec 2014 15:47
URI: http://trap.ncirl.ie/id/eprint/1883

Actions (login required)

View Item View Item