Teaching

Master of sport analytics

PSA - Principles of Sports Analytics (2018, 2019, 2020)

In this subject, students will explore the fundamental principles of analytics within the context of sporting environments.Students will be introduced to the mathematical and statistical architecture and rationale that underpins a range of sports analytics methods. The basic practices of handling, cleaning and processing data that is generated from sport will be examined. Students will learn basic programming and coding skills to analyse sport-related data.

SAP - Sports Analytics in Practice (2018, 2019)

In this subject, students will apply their theoretical understanding of analytics processes and methodologies to authentic sport-related data sets. Students will develop an analysis plan and implement this plan in order to formulate specific outcomes arising from their data analysis. Students will use appropriate visual analytics tools to present their data in order to communicate formulated outcomes and findings.

SDC - Sports Data Capture (2018, 2020)

In this subject, students will be introduced to the available technology applications that generate data from sport. Students will systematically appraise data capture technology using accepted criteria in order to identify the limitations of available technology in sport data capture. Students will explore the factors that influence effective and accurate data capture in sport and its handling and treatment. Using their understanding of these factors and available technology applications, students will learn to identify appropriate applications and processes for a range of analysis scenarios.

Supervision

Master of sport analytics research theses:

Industry partners shown in brackets.

• 2020
  • Analysis of centre bounce and centre field stoppage strategies in AFL. (St. Kilda Football Club)
  • A machine learning approach to dynamic win probability in AFL. (Carlton Football Club)
  • Automation of GPS data analysis for sport science. (Melbourne Rebels)
  • Rugby Union: Investigating the Potential Gain from Different 22-Metre Kicking Strategies.
  • Predicting professional athletes’ career outcomes using a nearest neighbour model.
• 2019
  • Constructing a field equity model for Rugby League using location data and phases of play. (Champion Data)
• 2018
  • What is ‘Draftable’ in Australian Rules Football. (AFL Victoria)
  • Optimising First Serve Selection in Men’s Professional Tennis Using Hawk-Eye Data. (Tennis Australia)
  • Common Rider Type Combinations in World Tour Cycling Teams. (Dimension Data Cycling Team)
  • Team Cohesion and Player Performance in NBA Basketball. (GainLine Analytics)
  • Does ball movement efficiency impact the scoring output of successful sides in the Australian Football League?
  • Modelling Team Sports with Bayesian Networks.

Short courses

• 3-day Sports Analytics Intensive at the Austrailan Institute of Sport (AIS).