Abstract
The Australian Football League (AFL) is a fast-paced invasion style ball game where two teams of 18 players jockey for a position through the strategic use of on-field tactics and skills. Each match consists of four quarters which range in length from 20 to 40 min and are heavily influenced by the irregular nature of game stoppages. The purpose of this study was to identify whether it was possible to model and subsequently forecast match outcome based on both prior match information as well as real-time transactional data. 23 professional level matches were analysed with each match containing an average of 1907 transactional epochs. To account for the irregular frequency at which each epoch occurs, a time-inhomogeneous Markov process was adopted, with model evaluation assessed on both epoch accuracy and final match result. The model performed notably well with an average epoch accuracies in excess of 71% and match outcome results in excess of 78%. The results of this study demonstrate that accurate near real-time prediction is achievable under real-world conditions using real match AFL transactional data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The Western Bulldogs is a professional AFL team headquartered in the Australian state of Victoria.
- 2.
The recalculated probability of a home team winning any given match after the home and away team reallocation described above.
- 3.
The percentage of games over the past 6 games for which the home team i has won against the away team j.
- 4.
The percentage of games over the past 5 games for which the home team i has won against any opponent a.
- 5.
The percentage of games over the past 5 games for which the away team j has won against any opponent a.
- 6.
The score margin with respect to the home team i at time t.
- 7.
The result with respect to the home team i at time t.
References
Australian Football League: Laws of Australian football (2015)
K. Shirley, A markov model for basketball, in New England Symposium for Statistics in Sports (2007)
E. Štrumbelj, P. Vračar, Simulating a basketball match with a homogeneous markov model and forecasting the outcome. Int. J. Forecast. 28(2), 532–542 (2012). https://doi.org/10.1016/j.ijforecast.2011.01.004, http://www.sciencedirect.com/science/article/pii/S0169207011000458
S. Akhtar, P. Scarf, Forecasting test cricket match outcomes in play. Int. J. Forecast. 28(3), 632–643 (2012). https://doi.org/10.1016/j.ijforecast.2011.08.005, http://www.sciencedirect.com/science/article/pii/S0169207011001622
S. Robertson, N. Back, J.D. Bartlett, Explaining match outcome in elite australian rules football using team performance indicators. J. Sports Sci. (ahead-of-print), 1–8 (2015)
AFL Tables: Afl-vfl match, player and coaching stats, records and lists (2015). http://afltables.com
S. Reicher, The psychology of crowd dynamics, in Blackwell Handbook of Social Psychology: Group Processes (2001), pp. 182–208
R. Stefani, S. Clarke, Predictions and home advantage for australian rules football. J. Appl. Stat. 19(2), 251–261 (1992)
S.R. Clarke, Home advantage in the Australian football league. J. Sports Sci. 23(4), 375–385 (2005)
R Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2018). https://www.R-project.org/
J. Kalbfleisch, J. Lawless, The analysis of panel data under a markov assumption. J. Am. Stat. Assoc. 863–871 (1985)
D.W. Hosmer Jr., S. Lemeshow, R.X. Sturdivant, Applied Logistic Regression, vol. 398 (Wiley, New York, 2013)
D.O. Logofet, E.V. Lesnaya, The mathematics of markov models: what markov chains can really predict in forest successions. Ecolo. Model. 126(2), 285 – 298 (2000). https://doi.org/10.1016/S0304-3800(00)00269-6, http://www.sciencedirect.com/science/article/pii/S0304380000002696
G. Marshall, R.H. Jones, Multi-state models and diabetic retinopathy. Stat. Med. 14(18), 1975–1983 (1995)
C.H. Jackson, Multi-state models for panel data: the msm package for R. J. Stat. Softw. 38(8), 1–29 (2011). http://www.jstatsoft.org/v38/i08/
W.N. Venables, B.D. Ripley, Modern Applied Statistics with S (Springer, New York, 2002)
V. Goulet, C. Dutang, M. Maechler, D. Firth, M. Shapira, M. Stadelmann, expm: matrix exponential, log, ’etc’ (2017). https://CRAN.R-project.org/package=expm. R package version 0.999-2
H. Wickham, ggplot2: Elegant Graphics for Data Analysis (Springer, New York, 2009). http://ggplot2.org
Acknowledgements
Champion Data and AFL Tables for supplying the data used in this study.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The authors would like to acknowledge the contribution of an Australian Government Research Training Program Scholarship in supporting this research.
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Josman, C., Gupta, R., Robertson, S. (2020). Markov Chain Models for the Near Real-Time Forecasting of Australian Football League Match Outcomes. In: Nagar, A., Deep, K., Bansal, J., Das, K. (eds) Soft Computing for Problem Solving 2019 . Advances in Intelligent Systems and Computing, vol 1139. Springer, Singapore. https://doi.org/10.1007/978-981-15-3287-0_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-3287-0_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3286-3
Online ISBN: 978-981-15-3287-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)