Journal article
Evaluating Australian Football League player contributions using interactive network simulation
Journal of Sports Science and Medicine, Vol.12(1), pp.116-121
2013
Abstract
This paper focuses on the contribution of Australian Football League (AFL) players to their team's on-field network by simulating player interactions within a chosen team list and estimating the net effect on final score margin. A Visual Basic computer program was written, firstly, to isolate the effective interactions between players from a particular team in all 2011 season matches and, secondly, to generate a symmetric interaction matrix for each match. Negative binomial distributions were fitted to each player pairing in the Geelong Football Club for the 2011 season, enabling an interactive match simulation model given the 22 chosen players. Dynamic player ratings were calculated from the simulated network using eigenvector centrality, a method that recognises and rewards interactions with more prominent players in the team network. The centrality ratings were recorded after every network simulation and then applied in final score margin predictions so that each player's match contribution-and, hence, an optimal team-could be estimated. The paper ultimately demonstrates that the presence of highly rated players, such as Geelong's Jimmy Bartel, provides the most utility within a simulated team network. It is anticipated that these findings will facilitate optimal AFL team selection and player substitutions, which are key areas of interest to coaches. Network simulations are also attractive for use within betting markets, specifically to provide information on the likelihood of a chosen AFL team list "covering the line".
Details
- Title
- Evaluating Australian Football League player contributions using interactive network simulation
- Authors
- J Sargent (Author) - RMIT UniversityAnthony Bedford (Author) - RMIT University
- Publication details
- Journal of Sports Science and Medicine, Vol.12(1), pp.116-121
- Publisher
- Journal of Sports Science and Medicine
- Date published
- 2013
- ISSN
- 1303-2968; 1303-2968
- Organisation Unit
- University of the Sunshine Coast, Queensland; School of Science, Technology and Engineering; School of Health and Behavioural Sciences - Legacy
- Language
- English
- Record Identifier
- 99451489702621
- Output Type
- Journal article
Metrics
160 Record Views