Australian
Rules football
Analysis
of the Swinburne Computer Performance in Identifying Inefficiencies in the AFL
Betting Market
Stefan Yelas
A thesis submitted
as partial fulfilment of the requirement for the degree of Master of Science
in Applied Statistics at Swinburne University of Technology
October 2003
Abstract
This thesis
analyses the performance of the Swinburne Computer in predicting the outcome
of Australian Football League (AFL) games and identifying potential inefficiencies
in the AFL sports betting market.
Data consisted
of the names of the AFL teams playing, the game location, the game outcomes
(points scored by each team), dates, prices for the head-to-head bets by TabCorp,
and the probabilities of a team winning produced by the Swinburne Computer for
each game in the home and away seasons 1998 to 2002.
Analysis showed
that betting strategies using certain overlay levels predicted by the Swinburne
Computer are successful in identifying statistical inefficiencies in the AFL
betting market.
For a copy
of this thesis in MS Word format please e-mail guywest_at_ozmium_dot_com_dot_au
Total size
3.14 megabytes.
AFL
index page
Stephen
Clarke CV 
AFL
package and pricing
Testimonials
Clarke
media articles
Home|FAQs|Disclaimer|Contact
Us
©2000
to present Ozmium Pty Ltd. All rights reserved
