1. bookVolume 20 (2021): Issue 1 (July 2021)
Journal Details
License
Format
Journal
eISSN
1684-4769
First Published
16 Apr 2016
Publication timeframe
2 times per year
Languages
English
access type Open Access

Can Elite Australian Football Player’s Game Performance Be Predicted?

Published Online: 10 Aug 2021
Volume & Issue: Volume 20 (2021) - Issue 1 (July 2021)
Page range: 55 - 78
Journal Details
License
Format
Journal
eISSN
1684-4769
First Published
16 Apr 2016
Publication timeframe
2 times per year
Languages
English
Abstract

In elite Australian football (AF) many studies have investigated individual player performance using a variety of outcomes (e.g. team selection, game running, game rating etc.), however, none have attempted to predict a player’s performance using combinations of pre-game factors. Therefore, our aim was to investigate the ability of commonly reported individual player and team characteristics to predict individual Australian Football League (AFL) player performance, as measured through the official AFL player rating (AFLPR) (Champion Data). A total of 158 variables were derived for players (n = 64) from one AFL team using data collected during the 2014-2019 AFL seasons. Various machine learning models were trained (cross-validation) on the 2014-2018 seasons, with the 2019 season used as an independent test set. Model performance, assessed using root mean square error (RMSE), varied (4.69-5.03 test set RMSE) but was generally poor when compared to a singular variable prediction (AFLPR pre-game rating: 4.72 test set RMSE). Variation in model performance (range RMSE: 0.14 excusing worst model) was low, indicating different approaches produced similar results, however, glmnet models were marginally superior (4.69 RMSE test set). This research highlights the limited utility of currently collected pre-game variables to predict week-to-week game performance more accurately than simple singular variable baseline models.

Keywords

Alexander, J. P., Spencer, B., Sweeting, A. J., Mara, J. K., & Robertson, S. (2019). The influence of match phase and field position on collective team behaviour in Australian Rules football. Journal of Sports Sciences, 37(15), 1699-1707. doi:10.1080/02640414.2019.158607710.1080/02640414.2019.158607730836845 Search in Google Scholar

Apley, D. W. (2016). Visualizing the effects of predictor variables in black box supervised learning models. arXiv.org, 1-36. Retrieved from https://arxiv.org/abs/1612.08468 Search in Google Scholar

Beretta, L., & Santaniello, A. (2016). Nearest neighbor imputation algorithms: A critical evaluation. BMC Medical Informatics and Decision Making, 16(Suppl. 3), 74. doi:10.1186/s12911-016-0318-z10.1186/s12911-016-0318-z495938727454392 Search in Google Scholar

Burgess, D., Naughton, G., & Hopkins, W. (2012). Draft-camp predictors of subsequent career success in the Australian Football League. Journal of Science and Medicine in Sport, 15(6), 561-567. doi:10.1016/j.jsams.2012.01.00610.1016/j.jsams.2012.01.00622710084 Search in Google Scholar

Colangelo, A. (2017, November 4). Mindfulness and meditation helped Richmond break their AFL premiership drought. The Age. Retrieved from https://www.theage.com.au/sport/afl/mindfulness-and-meditation-helped-richmond-break-afl-premiership-drought-20171103-gzed1o.html Search in Google Scholar

Colby, M. J., Dawson, B., Heasman, J., Rogalski, B., & Gabbett, T. J. (2014). Accelerometer and GPS-derived running loads and injury risk in elite Australian footballers. Journal of Strength and Conditioning Research, 28(8), 2244-2252. doi:10.1519/JSC.000000000000036210.1519/JSC.000000000000036225054573 Search in Google Scholar

Colby, M. J., Dawson, B., Peeling, P., Heasman, J., Rogalski, B., Drew, M. K., & Stares, J. (2018). Improvement of prediction of noncontact injury in elite Australian footballers with repeated exposure to established high-risk workload scenarios. International Journal of Sports Physiology and Performance, 13(9), 1130-1135. doi:10.1123/ijspp.2017-069610.1123/ijspp.2017-069629543079 Search in Google Scholar

Colby, M. J., Dawson, B., Peeling, P., Heasman, J., Rogalski, B., Drew, M. K., . . . Lester, L. (2017). Multivariate modelling of subjective and objective monitoring data improve the detection of non-contact injury risk in elite Australian footballers. Journal of Science and Medicine in Sport, 20(12), 1068-1074. doi:10.1016/j.jsams.2017.05.01010.1016/j.jsams.2017.05.01028595869 Search in Google Scholar

Drew, M. K., & Finch, C. F. (2016). The relationship between training load and injury, iIllness and soreness: A systematic and literature review. Sports Medicine, 46(6), 861-883. doi:10.1007/s40279-015-0459-810.1007/s40279-015-0459-826822969 Search in Google Scholar

Drew, M. K., Raysmith, B. P., & Charlton, P. C. (2017). Injuries impair the chance of successful performance by sportspeople: A systematic review. British Journal of Sports Medicine, 51(16), 1209-1214. doi:10.1136/bjsports-2016-09673110.1136/bjsports-2016-09673128446456 Search in Google Scholar

Eckard, T. G., Padua, D. A., Hearn, D. W., Pexa, B. S., & Frank, B. S. (2018). The relationship between training load and injury in athletes: A systematic review. Sports Medicine, 48(8), 1929-1961. doi:10.1007/s40279-018-0951-z10.1007/s40279-018-0951-z29943231 Search in Google Scholar

Eirale, C., Tol, J. L., Farooq, A., Smiley, F., & Chalabi, H. (2013). Low injury rate strongly correlates with team success in Qatari professional football. British Journal of Sports Medicine, 47(12), 807-808. doi:10.1136/bjsports-2012-09104010.1136/bjsports-2012-091040371777922904292 Search in Google Scholar

Fahey-Gilmour, J., Dawson, B., Peeling, P., Heasman, J., & Rogalski, B. (2019). Multifactorial analysis of factors influencing elite Australian football match outcomes: A machine learning approach. International Journal of Computer Science in Sport, 18(3), 100-124. doi:10.2478/ijcss-2019-002010.2478/ijcss-2019-0020 Search in Google Scholar

Friedman, J., Hastie, T., & Tibshirani, R. (2010). Regularization paths for generalized linear models via coordinate descent. Journal of Statistical Software, 33(1), 1-22.10.18637/jss.v033.i01 Search in Google Scholar

Gabelich, J. (2018). ‘Football IQ off the charts’: David King says Carlton teen Zac Fisher uses the ball like Sam Mitchell. Retrieved from Fox Sports website: https://www.foxsports.com.au/afl/football-iq-off-the-charts-david-king-says-carlton-teen-zac-fisher-uses-the-ball-like-sam-mitchell/news-story/0dc4de3fc820400a936d577c25277fbf Search in Google Scholar

Gastin, P. B., Fahrner, B., Meyer, D., Robinson, D., & Cook, J. L. (2013). Influence of physical fitness, age, experience, and weekly training load on match performance in elite Australian football. Journal of Strength and Conditioning Research, 27(5), 1272-1279. doi:10.1519/JSC.0b013e318267925f10.1519/JSC.0b013e318267925f22820206 Search in Google Scholar

Hagglund, M., Walden, M., Magnusson, H., Kristenson, K., Bengtsson, H., & Ekstrand, J. (2013). Injuries affect team performance negatively in professional football: An 11-year follow-up of the UEFA Champions League injury study. British Journal of Sports Medicine, 47(12), 738-742. doi:10.1136/bjsports-2013-09221510.1136/bjsports-2013-09221523645832 Search in Google Scholar

Impellizzeri, F. M., Rampinini, E., Coutts, A. J., Sassi, A., & Marcora, S. M. (2004). Use of RPE-based training load in soccer. Medicine and Science in Sports and Exercise, 36(6), 1042-1047. doi:10.1249/01.mss.0000128199.23901.2f10.1249/01.MSS.0000128199.23901.2F15179175 Search in Google Scholar

Jackson, K. (2016). Assessing player performance in Australian football using spatial data. (Doctor of Philosophy), Swinburne University of Technology, Melbourne, Australia. Search in Google Scholar

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning (1 ed.). New York: Springer.10.1007/978-1-4614-7138-7 Search in Google Scholar

Johnston, R. D., Black, G. M., Harrison, P. W., Murray, N. B., & Austin, D. J. (2018). Applied sport science of Australian football: A systematic review. Sports Medicine, 48(7), 1673-1694. doi:10.1007/s40279-018-0919-z10.1007/s40279-018-0919-z29633084 Search in Google Scholar

Johnston, R. J., Watsford, M. L., Pine, M. J., Spurrs, R. W., Murphy, A., & Pruyn, E. C. (2012). Movement demands and match performance in professional Australian football. International Journal of Sports Medicine, 33(2), 89-93. doi:10.1055/s-0031-128779810.1055/s-0031-128779822095328 Search in Google Scholar

Karatzoglou, A., Smola, A., Hornik, K., & Zeileis, A. (2004). kernlab - an S4 package for kernel methods in R. Journal of Statistical Software, 11(9), 1-20. doi:10.18637/jss.v011.i0910.18637/jss.v011.i09 Search in Google Scholar

Kuhn, M. (2017). caret: Classification and regression training (Version 6.0-76.). Retrieved from https://CRAN.R-project.org/package=caret Search in Google Scholar

Kuhn, M., & Johnson, K. (2016). Applied Predictive Modeling. (pp. 600). doi:10.1007/978-1-4614-6849-310.1007/978-1-4614-6849-3 Search in Google Scholar

Kuhn, M., & Wickham, H. (2018). recipes: Preprocessing tools to create design matrices (Version 0.1.3.). Retrieved from https://CRAN.R-project.org/package=recipes Search in Google Scholar

Lazarus, B. H., Stewart, A. M., White, K. M., Rowell, A. E., Esmaeili, A., Hopkins, W. G., & Aughey, R. J. (2017). Proposal of a global training load measure predicting match performance in an elite team sport. Frontiers in Physiology, 8, 930. doi:10.3389/fphys.2017.0093010.3389/fphys.2017.00930570231129209229 Search in Google Scholar

Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R News, 2(3), 18-22. Search in Google Scholar

Malone, J. J., Lovell, R., Varley, M. C., & Coutts, A. J. (2017). Unpacking the black box: Applications and considerations for using GPS devices in sport. International Journal of Sports Physiology and Performance, 12(Suppl. 2), S218-S226. doi:10.1123/ijspp.2016-023610.1123/ijspp.2016-023627736244 Search in Google Scholar

McCaskie, C. J., Young, W. B., Fahrner, B. B., & Sim, M. (2018). Association between pre-season training and performance in elite Australian football. International Journal of Sports Physiology and Performance, 14(1), 68-75. doi:10.1123/ijspp.2018-007610.1123/ijspp.2018-007630117344 Search in Google Scholar

McIntosh, S., Kovalchik, S., & Robertson, S. (2019). Comparing subjective and objective evaluations of player performance in Australian Rules football. PloS One, 14(8), e0220901. doi:10.1371/journal.pone.022090110.1371/journal.pone.0220901669376231412064 Search in Google Scholar

Milborrow, S. (2018). earth: Multivariate adaptive regression splines (Version 4.6.3). Retrieved from https://CRAN.R-project.org/package=earth Search in Google Scholar

Molnar, C. (2018). Interpretable Machine Learning. Retrieved from https://christophm.github.io/interpretable-ml-book/ Search in Google Scholar

Molnar, C., Bischl, B., & Casalicchio, G. (2018). iml: An R package for interpretable machine learning. Journal of Open Source Software, 3(26), 786. doi:10.21105/joss.0078610.21105/joss.00786 Search in Google Scholar

Mooney, M., O’Brien, B., Cormack, S., Coutts, A., Berry, J., & Young, W. (2011). The relationship between physical capacity and match performance in elite Australian football: A mediation approach. Journal of Science and Medicine in Sport, 14(5), 447-452. doi:10.1016/j.jsams.2011.03.01010.1016/j.jsams.2011.03.01021530392 Search in Google Scholar

Pink, M. A. (2015). Relationships between AFL player off-field activity player characteristics, the club environment and on-field engagement. (Doctor of Philosophy), Australian Catholic University, Fitzroy, Australia. Search in Google Scholar

R Core Team. (2018). R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing. Retrieved from https://www.R-project.org/ Search in Google Scholar

Robertson, S., Gupta, R., & McIntosh, S. (2016). A method to assess the influence of individual player performance distribution on match outcome in team sports. Journal of Sports Sciences, 34(19), 1893-1900. doi:10.1080/02640414.2016.114210610.1080/02640414.2016.114210626853070 Search in Google Scholar

Rogalski, B., Dawson, B., Heasman, J., & Gabbett, T. J. (2013). Training and game loads and injury risk in elite Australian footballers. Journal of Science and Medicine in Sport, 16(6), 499-503. doi:10.1016/j.jsams.2012.12.00410.1016/j.jsams.2012.12.00423333045 Search in Google Scholar

RStudio Team. (2018). RStudio: Integrated Development for R. Boston: RStudio Incorporated. Retrieved from http://www.rstudio.com/ Search in Google Scholar

Ryan, S., Coutts, A. J., Hocking, J., Dillon, P. A., Whitty, A., & Kempton, T. (2018). Physical preparation factors that influence technical and physical match performance in professional Australian football. International Journal of Sports Physiology and Performance, 13(8), 1021-1027. doi:10.1123/ijspp.2017-064010.1123/ijspp.2017-064029466065 Search in Google Scholar

Spencer, B., Jackson, K., Bedin, T., & Robertson, S. (2019). Modeling the quality of player passing decisions in Australian Rules football relative to risk, reward, and commitment. Frontiers in Psychology, 10, 1777. doi:10.3389/fpsyg.2019.0177710.3389/fpsyg.2019.01777668858431428026 Search in Google Scholar

Stares, J., Dawson, B., Heasman, J., & Rogalski, B. (2015). Relationship between pre-season strength and power measures and performance in elite Australian football. International Journal of Performance Analysis in Sport, 15(3), 777-793.10.1080/24748668.2015.11868830 Search in Google Scholar

Sullivan, C., Bilsborough, J. C., Cianciosi, M., Hocking, J., Cordy, J. T., & Coutts, A. J. (2014). Factors affecting match performance in professional Australian football. International Journal of Sports Physiology and Performance, 9(3), 561-566. doi:10.1123/ijspp.2013-018310.1123/ijspp.2013-0183 Search in Google Scholar

Therneau, T., & Atkinson, B. (2018). rpart: Recursive partitioning and regression trees (Version 4.1-13). Retrieved from https://CRAN.R-project.org/package=rpart Search in Google Scholar

Venables, W. N., & Ripley, B. D. (2002). Modern applied statistics with S (4 ed.). New York: Springer.10.1007/978-0-387-21706-2 Search in Google Scholar

Waldron, M., Worsfold, P., Twist, C., & Lamb, K. (2011). Concurrent validity and test-retest reliability of a global positioning system (GPS) and timing gates to assess sprint performance variables. Journal of Sports Sciences, 29(15), 1613-1619. doi:10.1080/02640414.2011.60870310.1080/02640414.2011.608703 Search in Google Scholar

Wickham, H., Averick, M., Bryan, J., Chang, W., McGowan, L., François, R., . . . Yutani, H. (2019). Welcome to the Tidyverse. Journal of Open Source Software, 4(43), 1686. doi:10.21105/joss.0168610.21105/joss.01686 Search in Google Scholar

Windt, J., Gabbett, T. J., Ferris, D., & Khan, K. M. (2017). Training load--injury paradox: Is greater preseason participation associated with lower in-season injury risk in elite rugby league players? British Journal of Sports Medicine, 51(8), 645-650. doi:10.1136/bjsports-2016-09597310.1136/bjsports-2016-095973 Search in Google Scholar

Yeo, I.-K., & Johnson, R. A. (2000). A new family of power transformations to improve normality or symmetry. Biometrika, 87(4), 954-959.10.1093/biomet/87.4.954 Search in Google Scholar

Young, W. B., Newton, R. U., Doyle, T. L., Chapman, D., Cormack, S., Stewart, G., & Dawson, B. (2005). Physiological and anthropometric characteristics of starters and non-starters and playing positions in elite Australian Rules football: A case study. Journal of Science and Medicine in Sport, 8(3), 333-345. doi:10.1016/S1440-2440(05)80044-110.1016/S1440-2440(05)80044-1 Search in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo