Volume : 2, Issue : 5, MAY 2016

THE RUGBY LEAGUE PREDICTION MODEL: USING AN ELOBASED APPROACH TO PREDICT THE OUTCOME OF NATIONAL RUGBY LEAGUE (NRL) MATCHES

Joel Carbone, Tony Corke, Dr. Frank Moisiadis

Abstract

We introduce and discuss our model, which is used for rating teams in the National Rugby League (NRL) competition. It is an ELO-style model, modified to integrate several match variables into its calculations. Match data obtained from the 1999-2014 NRL seasons were used to build the model, and matches from the 2015 NRL season were used as a test sample. An automated computer system, employing an iterative approach, and written in R script, was used to optimise the parameters in the underlying ELO model. The model correctly predicted a total 63.0% of results, with a mean absolute error (MAE) of 13.7 points per game during the build process. The test phase saw a slightly better MAE – of 13.0 points per game – produced, and a lower accuracy of 55.7%. Secondary experiments regarding the model's ability to predict the top 8 at the end of the home-and-away season were also conducted.

Keywords

NRL, rating, ELO, predictive, rugby league.

Article : Download PDF

Cite This Article

Article No : 10

Number of Downloads : 1055

References

Alamar, B. (2013). Sports Analytics: A Guide for Coaches, Managers and Other Decision Makers. New York, NY: Columbia University Press.

Barrett, C. (2010, April 22). Melbourne Storm stripped of premierships for salary cap breaches. The Sydney Morning Herald. Retrieved from http://www.smh.com.au/rugby-league/league-news/melbourne-storm-stripped-of-premierships-for-salary-cap-breaches-20100422-td91.html

Constantinou, A. C., Fenton, N. E., & Neil, M. (2012).pi-football: A Bayesian network model for forecasting Association Football match outcomes.Knowledge-Based Systems36, 322-339.

Eaves, S., & Broad, G. (2007).A comparative analysis of professional rugby league football playing patterns between Australia and the United Kingdom. International Journal of Performance Analysis of Sport, 7(3), 54–63.

Gabbett, T., Jenkins, D., & Abernethy, B. (2012). Physical demands of professional rugby league training and competition using microtechnology. Journal of Science and Medicine in Sport, 15(1), 80–86. 

Glickman, M. E. (1995).The glicko system. Boston University.

Hunter, L. (2014, July 21). How Sports Data Analytics Is Upsetting The Game All Over Again. Retrieved from http://www.fastcolabs.com/3033324/how-sports-data-analytics-is-upsetting-the-game-all-over-again

Hvattum, L. M., &Arntzen, H. (2010). Using ELO ratings for match result prediction in association football. International Journal of forecasting26(3), 460-470.

Jancetic, S. (2009, April 4).Bulldogs stripped of two NRL points. Retrieved from http://www.theroar.com.au/2009/04/04/bulldogs-stripped-of-two-nrl-points/

Kempton, T., Kennedy, N., & Coutts, A. J. (2015). The expected value of possession in professional rugby league match-play. Journal of sports sciences, 1-6.

Kempton, T., Sirotic, A., Rampinini, E.,& Coutts, A. J. (2013). Match-related fatigue reduces physical and technical performance during elite rugby league match-play: A case study. Journal of Sports Sciences, 31(16), 1770–1780. 

Kvam, P., &Sokol, J. S. (2006). A logistic regression/Markov chain model for NCAA basketball. Naval Research Logistics (NrL)53(8), 788-803.

Lasek, J., Szlávik, Z., &Bhulai, S. (2013). The predictive power of ranking systems in association football.International Journal of Applied Pattern Recognition, 1(1), 27–46.

McLellan, C. P. (2010). NEUROMUSCULAR, BIOCHEMICAL, ENDOCRINE AND PHYSIOLOGICAL RESPONSES OF ELITE RUGBY LEAGUE PLAYERS TO COMPETITIVE MATCH-PLAY (Doctoral dissertation, Bond University).

Medeiros, J. (2014, January 23). The winning formula: data analytics has become the latest tool keeping football teams one step ahead. Retrieved from http://www.wired.co.uk/magazine/archive/2014/01/features/the-winning-formula

Microsoft. (2010). Microsoft Excel [computer software]. Redmond, Washington: Microsoft.

Neumann, C., Duboscq, J., Dubuc, C., Ginting, A., Irwan, A. M., Agil, M., Widdig, A.,&Engelhardt, A. (2011). Assessing dominance hierarchies: validation and advantages of progressive evaluation with Elo-rating. Animal Behaviour82(4), 911-921.

National Rugby League - 2015 FINAL. (2015). Retrieved from http://www.rugbyleagueratings.com/2015nrl.php

Paine, N. (2015, September 10).NFL Elo Ratings Are Back!. Retrieved from http://fivethirtyeight.com/datalab/nfl-elo-ratings-are-back/

R Core Team (2015). R: A language and environment for statistical   computing. R Foundation for Statistical Computing, Vienna, Austria.  http://www.R-project.org/.

Rampinini, E., Impellizzeri, F. M., Castagna, C., Coutts, A. J., &Wisloff, U. (2009). Technical performance during soccer matches of the Italian SerieA league: Effect of fatigue and competitive level. Journal of Science and Medicine in Sport12(1), 227-233.

Ross, D. (2007, December 16). Arpad Elo and the Elo Rating System. Retrieved from http://en.chessbase.com/post/arpad-elo-and-the-elo-rating-system

Ryall, R., & Bedford, A. (2010). An optimized ratings-based model for forecasting Australian Rules football. International Journal of Forecasting26(3), 511-517.

Sullivan, C., Bilsborough, J., Cianciosi, M., Hocking, J., Cordy, J., & Coutts, A. J. (2014). Match score affects activity profile and skill performance in professional Australian football players. Journal of Science and Medicine in Sport, 17(3), 326–331.

Silver, N., & Fischer-Baum, R. (2015, May 21).How We Calculate NBA Elo Ratings. Retrieved from http://fivethirtyeight.com/features/how-we-calculate-nba-elo-ratings/

Silver, N. (2006, June 28).Lies, Damned Lies. Retrieved from http://www.baseballprospectus.com/article.php?articleid=5247

Sirotic, A., Knowles, H., Catterick, C., & Coutts, A. J. (2011). Positional match demands of professional Rugby League Competition. Journal of Strength and Conditioning Research, 25(11), 3076–3087. 

Waldron, M., Twist, C., Highton, J., Worsfold, P., & Daniels, M. (2011).Movement and physiological match demands of elite rugby league using portable global positioning systems. Journal of Sports Sciences, 29(11), 1223–1230. 

Walters, B.,& Masters, R. (2002, August 24). Bulldogs stripped of points. The Age. Retrieved from http://www.theage.com.au/articles/2002/08/23/1030052974663.html

Williams, S. (2006, February 27). Warriors docked points and fined. Retrieved from http://leagueunlimited.com/news/warriors-docked-points-and-fined#MIWBu6g3ALkmzeIq.97

Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research30(1), 79.

Yang, T. Y., & Swartz, T. (2004).A two-stage Bayesian model for predicting winners in major league baseball. Journal of Data Science2(1), 61-73.

Ziemba, B. (2015). The 2014–2015 NFL Season, Playoffs, and the Super Bowl.Wilmott2015(77), 24-43.