Abstract
Statistical analysis in competitive sport is an important tool for developing strategy and seeking competitive advantages. However, for complex team sports such as Australian Rules Football, major limitations occur when using possession event data for game analysis. First, focusing on counting possession events does not capture the impact of off-the-ball actions such as ground positioning of other players. Second, it is difficult to determine the extent that an event is due to either team’s relative proficiency or skill. Third, there is limited possession event data available from each match and modelling efforts often have low statistical power. Here we reinterpret event data into positional systems and utilise pairwise performance metrics to understand the relative team proficiency in each of these states. These metrics can then be used to construct transition probabilities between states for future games, and ultimately, absorbing probabilities of goal states. Our approach effectively predicts match outcomes using team ratings for forward, midfield and defensive systems and is sufficiently interpretable to support strategic decision-making by coaching departments in the Australian Football League (AFL).
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: None declared.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
Aldous, D. 2017. “Elo Ratings and the Sports Model: A Neglected Topic in Applied Probability?” Statistical Science 32: 616–29. https://doi.org/10.1214/17-sts628.Search in Google Scholar
Atkinson, G., and A. M. Nevill. 2001. “Selected Issues in the Design and Analysis of Sport Performance Research.” Journal of Sports Sciences 19: 811–27. https://doi.org/10.1080/026404101317015447.Search in Google Scholar PubMed
Azhari, H., Y. Widyaningsih, and D. Lestari. 2018. “Predicting Final Result of Football Match Using Poisson Regression Model.” Journal of Physics: Conference Series 1108: 012066. https://doi.org/10.1088/1742-6596/1108/1/012066.Search in Google Scholar
Bialkowski, A., P. Lucey, P. Carr, Y. Yue, S. Sridharan, and I. Matthews. 2014. “Large-scale Analysis of Soccer Matches Using Spatiotemporal Tracking Data.” In 2014 IEEE International Conference on Data Mining, 725–30. IEEE.10.1109/ICDM.2014.133Search in Google Scholar
Braham, C., and M. Small. 2018. “Complex Networks Untangle Competitive Advantage in Australian Football.” Chaos: An Interdisciplinary Journal of Nonlinear Science 28: 053105. https://doi.org/10.1063/1.5006986.Search in Google Scholar PubMed
Brewer, C., B. Dawson, J. Heasman, G. Stewart, and S. Cormack. 2010. “Movement Pattern Comparisons in Elite (AFL) and Sub-elite (WAFL) Australian Football Games Using GPS.” Journal of Science and Medicine in Sport/Sports Medicine Australia 13: 618–23. https://doi.org/10.1016/j.jsams.2010.01.005.Search in Google Scholar PubMed
Cattelan, M., C. Varin, and D. Firth. 2013. “Dynamic Bradley–Terry Modelling of Sports Tournaments.” Journal of the Royal Statistical Society: Series C (Applied Statistics) 62: 135–50. https://doi.org/10.1111/j.1467-9876.2012.01046.x.Search in Google Scholar
Clarke, S. R. 2005. “Home Advantage in the Australian Football League.” Journal of Sports Sciences 23: 375–85. https://doi.org/10.1080/02640410500074391.Search in Google Scholar PubMed
Dawson, B., R. Hopkinson, B. Appleby, G. Stewart, and C. Roberts. 2004. “Player Movement Patterns and Game Activities in the Australian Football League.” Journal of Science and Medicine in Sport 7: 278–91. https://doi.org/10.1016/s1440-2440(04)80023-9.Search in Google Scholar PubMed
Elo, A. E. 1978. The Rating of Chess Players, Past and Present. New York: Arco Pub.Search in Google Scholar
Forbes, D. 2006. “Dynamic prediction of Australian Rules Football using real time performance statistics.” PhD thesis.Search in Google Scholar
Glickman, M. E. 2012. Example of the Glicko-2 System, 1–6. Boston: Boston University.Search in Google Scholar
Goldner, K. 2012. “A Markov Model of Football: Using Stochastic Processes to Model a Football Drive.” Journal of Quantitative Analysis in Sports 8: 1–18, https://doi.org/10.1515/1559-0410.1400.Search in Google Scholar
Greenham, G., A. Hewitt, and K. Norton. 2017. “A Pilot Study to Measure Game Style within Australian Football.” International Journal of Performance Analysis in Sport 17: 576–85. https://doi.org/10.1080/24748668.2017.1372163.Search in Google Scholar
Hirotsu, N., K. Inoue, K. Yamamoto, and M. Yoshimura. 2022. “Soccer as a Markov Process: Modelling and Estimation of the Zonal Variation of Team Strengths.” IMA Journal of Management Mathematics, https://doi.org/10.1093/imaman/dpab042.Search in Google Scholar
Leushuis, C. 2018. “Beating the Odds – a State Space Model for Predicting Match Results in the Australian Football League.” Quantitative methods in Business and Economics 2: 1–20, https://doi.org/10.26481/marble.2018.v2.613.Search in Google Scholar
McIntosh, S., S. Kovalchik, and S. Robertson. 2018. “Validation of the Australian Football League Player Ratings.” International Journal of Sports Science & Coaching 13: 1064–71. https://doi.org/10.1177/1747954118758000.Search in Google Scholar
O’Shaughnessy, D. M. 2006. “Possession versus Position: Strategic Evaluation in AFL.” Journal of Sports Science and Medicine 5: 533.Search in Google Scholar
Prasetio, D. 2016. “Predicting Football Match Results with Logistic Regression.” In 2016 International Conference on Advanced Informatics: Concepts, Theory and Application (ICAICTA), 1–5. IEEE.10.1109/ICAICTA.2016.7803111Search in Google Scholar
R Core Team. 2013. R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing. Also available at http://www.R-project.org/.Search in Google Scholar
R Core Team. 2019. R: A Language and Environment for Statistical Computing. Vienna: R Foundation for Statistical Computing. Also available at https://www.R-project.org/.Search in Google Scholar
Rosli, C. M. F. C. M., M. Z. Saringat, N. Razali, and A. Mustapha. 2018. “A Comparative Study of Data Mining Techniques on Football Match Prediction.” Journal of Physics: Conference Series 1020: 012003. https://doi.org/10.1088/1742-6596/1020/1/012003.Search in Google Scholar
Ryall, R. 2011. “Predicting outcomes in Australian Rules Football.” PhD thesis, RMIT University.Search in Google Scholar
Ryall, R., and A. Bedford. 2010. “An Optimized Ratings-Based Model for Forecasting Australian Rules Football.” International Journal of Forecasting 26: 511–7. https://doi.org/10.1016/j.ijforecast.2010.01.001.Search in Google Scholar
Shafizadeh, M., J. Sproule, and S. Gray. 2013. “The Emergence of Coordinative Structures during Offensive Movement for Goal-Scoring in Soccer.” International Journal of Performance Analysis in Sport 13: 612–23. https://doi.org/10.1080/24748668.2013.11868675.Search in Google Scholar
Singh, K. 2019. Introducing Expected Threat (XT). Also available at https://karun.in/blog/expected-threat.html.Search in Google Scholar
Spencer, B., S. Morgan, J. Zeleznikow, and S. Robertson. 2016. “Clustering Team Profiles in the Australian Football League Using Performance Indicators.” In Proceedings of the 13th Australasian Conference on Mathematics and Computers in Sport, 11–3. Melbourne.Search in Google Scholar
Stefani, R., and S. Clarke. 1992. “Predictions and Home Advantage for Australian Rules Football.” Journal of Applied Statistics 19: 251–61. https://doi.org/10.1080/02664769200000021.Search in Google Scholar
Therneau, T., B. Atkinson, and B. Ripley. 2019. Rpart: Recursive Partitioning and Regression Trees. Also available at https://CRAN.R-project.org/package=dplyr, r package version 2.15.0.Search in Google Scholar
Wickham, H., M. Averick, J. Bryan, W. Chang, L. D. McGowan, R. François, G. Grolemund, A. Hayes, L. Henry, J. Hester, M. Kuhn, T. L. Pedersen, E. Miller, S. M. Bache, K. Müller, J. Ooms, D. Robinson, D. P. Seidel, V. Spinu, K. Takahashi, D. Vaughan, C. Wilke, K. Woo, and H. Yutani. 2019. “Welcome to the Tidyverse.” Journal of Open Source Software 4: 1686. https://doi.org/10.21105/joss.01686.Search in Google Scholar
Williams, G. 2011. Data Mining with Rattle and R: The art of Excavating Data for Knowledge Discovery. New York: Springer Science & Business Media.10.1007/978-1-4419-9890-3Search in Google Scholar
Woods, T. C. 2016. “The Use of Team Performance Indicator Characteristics to Explain Ladder Position at the Conclusion of the Australian Football League Home and Away Season.” International Journal of Performance Analysis in Sport 16: 837–47. https://doi.org/10.1080/24748668.2016.11868932.Search in Google Scholar
Woods, C. T., S. Robertson, and N. F. Collier. 2017. “Evolution of Game-Play in the Australian Football League from 2001 to 2015.” Journal of Sports Sciences 35: 1879–87. https://doi.org/10.1080/02640414.2016.1240879.Search in Google Scholar PubMed
Zhu, C., R. H. Byrd, P. Lu, and J. Nocedal. 1997. “Algorithm 778: L-BFGS-B: Fortran Subroutines for Large-Scale Bound-Constrained Optimization.” ACM Transactions on Mathematical Software 23: 550–60. https://doi.org/10.1145/279232.279236.Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston