Discipline: 
Mathematics
Status: 
Available
Level: 
Honours Project
Level: 
Summer Project
Level: 
Winter Project
Supervisor(s): 
Dr Michael Forbes, Dr Alan Huang

Traditional models of player valuation in Rugby League use summary statistics to estimate the value of a player.  Some examples include: minutes played, tackles made, tackles missed, hit ups made, metres gained, tries scored, try assists, errors, penalties conceded and kick effectiveness.  However, these models do not include any consideration of game dynamics.  For example, an error made when leading or trailing by 20 points with 5 minutes to go has much less impact than an error when leading or trailing by 2 points with 5 minutes to go.

This project aims to build a better model of player valuation by considering game dynamics.  It will involve analysing detailed game data files and working with the coaching and recruitment staff of a major NRL team.  The tasks of the project may include:

  • Researching playing valuation models used in Rugby League and other sports.
  • Meeting with team staff to discuss factors to consider.
  • Parsing XML game data files to extract the relevant data.
  • Building one or more models (models may vary by position) and fitting it to known players and their fair market valuation (as provided by the club).
  • Preliminary evaluation using the model on a pool of up and coming players.

This project would suit a student who is a Rugby League fan with a good background in Statistics and Operations Research.