School of Electronics and Computer Science, University of Southampton, Southampton SO17 1BJ, UK e-mails: ryan.beal@soton.ac.uk, t.j.norman@soton.ac.uk, sdr1@soton.ac.uk"/>
Search
  • All Journals
Advanced Search
Search articles by Title, Author, Keywords, DOI
Submit Manuscript
7.7CiteScore
2.0Impact Factor
Advanced Search
MAP  >  The Knowledge Engineering Review
2019 Volume 34
Article Contents
Next Previous
REVIEW   Open Access    

Artificial intelligence for team sports: a survey

More Information
  • Abstract: The sports domain presents a number of significant computational challenges for artificial intelligence (AI) and machine learning (ML). In this paper, we explore the techniques that have been applied to the challenges within team sports thus far. We focus on a number of different areas, namely match outcome prediction, tactical decision making, player investments, fantasy sports, and injury prediction. By assessing the work in these areas, we explore how AI is used to predict match outcomes and to help sports teams improve their strategic and tactical decision making. In particular, we describe the main directions in which research efforts have been focused to date. This highlights not only a number of strengths but also weaknesses of the models and techniques that have been employed. Finally, we discuss the research questions that exist in order to further the use of AI and ML in team sports.
  • 加载中
  • Agosto , A., Cavaliere , G., Kristensen , D. & Rahbek , A.2016. Modeling corporate defaults: Poisson autoregressions with exogenous covariates (PARX). Journal of Empirical Finance38, 640–663.

    Google Scholar

    Alan , A. T., Costanza , E., Ramchurn , S. D., Fischer , J., Rodden , T. & Jennings , N. R.2015. Managing energy tariffs with agents: a field study of a future smart energy system at home. In Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable Computers.

    Google Scholar

    Alcorn , M. A.2018. (batter—pitcher)2vec: statistic-free talent modeling with neural player embeddings. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/1008.pdf.

    Google Scholar

    Anderson , C. & Sally , D.2014. The Numbers Game: Why Everything You Know About Football is Wrong. Penguin.

    Google Scholar

    Angelini , G. & De Angelis , L.2017. PARX model for football match predictions. Journal of Forecasting36(7), 795–807.

    Google Scholar

    Baboota , R. & Kaur , H.2018. Predictive analysis and modelling football results using machine learning approach for English Premier League. International Journal of Forecasting35(2), 741–755.

    Google Scholar

    Baio , G. & Blangiardo , M.2008. Bayesian hierarchical model for the prediction of football results. Journal of Applied Statistics37(2), 253–264.

    Google Scholar

    Baker , R. & McHale , I.2013. Forecasting exact scores in National Football League games. International Journal of Forecasting29(1), 112–130.

    Google Scholar

    Beck , Z., Teacy , L., Rogers , A. & Jennings , N. R.2016. Online planning for collaborative search and rescue by heterogeneous robot teams. In Proceedings of the 2016 International Conference on Autonomous Agents &38; Multiagent Systems, 1024–1033.

    Google Scholar

    Beilock , S. & Gray , R.2007. Why do athletes choke under pressure? In Handbook of sport psychology, Tenenbaum , G. & Eklund , R. C. (eds), 425–444.

    Google Scholar

    Bojinov , I. & Bornn , L.2016. The pressing game: optimal defensive disruption in soccer. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2016/02/1475-Other-Sports.pdf.

    Google Scholar

    Boon , B. H. & Sierksma , G.2003. Team formation: matching quality supply and quality demand. European Journal of Operational Research148, 277–292.

    Google Scholar

    Bornn , L., Ward , P. & Norman , D.2019. Training schedule confounds the relationship between acute:chronic workload ratio and injury. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2019/02/Training-Schedule-Confounds-the-Relationship-between-Acute-Chronic-Workload-Ratio-and-Injury.pdf.

    Google Scholar

    Boswell , J.2008. Fantasy sports: a game of skill that is implicitly legal under state law, and now explicitly legal under federal law. Cardozo Arts Entertainment Law Journal25, 1257–1278.

    Google Scholar

    Boulier , B. L. & Stekler , H. O.2003. Predicting the outcomes of National Football League games. International Journal of Forecasting19(2), 257–270.

    Google Scholar

    Bowen , L., Gross , A. S., Gimpel , M. & Li , F. X.2016. Accumulated workloads and the acute:chronic workload ratio relate to injury risk in elite youth football players. British Journal of Sports Medicine51(5), 452–459.

    Google Scholar

    Burke , B.2019. DeepQB: deep learning with player tracking to quantify quarterback decision-making & performance. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2019/02/DeepQB.pdf.

    Google Scholar

    Cappellari , L. & Jenkins , S. P.2003. Multivariate probit regression using simulated maximum likelihood. The Stata Journal3(3), 278–294.

    Google Scholar

    Cervone , D., D’Amour , A., Bornn , L. & Goldsberry , K.2014. POINTWISE: predicting points and valuing decisions in real time with NBA optical tracking data. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/09/cervone_ssac_2014.pdf.

    Google Scholar

    Chalkiadakis , G. & Boutilier , C.2012. Sequentially optimal repeated coalition formation under uncertainty. Autonomous Agents and Multi-Agent Systems24(3), 441–484.

    Google Scholar

    Clarke , S. R. & Norman , J. M.1995. Home ground advantage of individual clubs in English soccer. Journal of the Royal Statistical Society. Series D (The Statistician)44(4), 509–521.

    Google Scholar

    Cohn , D. A., Ghahramani , Z. & Jordan , M. I.1996. Active learning with statistical models. Journal of Artificial Intelligence Research4, 129–145.

    Google Scholar

    Collobert , R. & Weston , J.2008. A unified architecture for natural language processing: deep neural networks with multitask learning. In Proceedings of the 25th International Conference on Machine Learning. ACM, 160–167.

    Google Scholar

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

    Google Scholar

    Constantinou , A. C., Fenton , N. & Neil , M.2013. Profiting from an inefficient association football gambling market: prediction, risk and uncertainty using Bayesian networks. Knowledge-Based Systems50, 60–86.

    Google Scholar

    Correia , V., Araujo , D., Craig , C. & Passos , P.2011. Prospective information for pass decisional behavior in rugby union. Human Movement Science30(5), 984–997.

    Google Scholar

    Coulom , R.2007. Computing Elo ratings of move patterns in the game of go. ICGA Journal30(4), 198–208.

    Google Scholar

    Crowder , M., Dixon , M., Ledford , A. & Robinson , M.2002. Dynamic modelling and prediction of English Football League matches for betting. Journal of the Royal Statistical Society. Series D (The Statistician)51(2), 157–168.

    Google Scholar

    Cust , E., Sweeting , A., Ball , K. & Robertson , S.2018. Machine and deep learning for sport-specific movement recognition: a systematic review of model development and performance. Journal of Sports Sciences37(5), 568–600.

    Google Scholar

    Dang , V. D., Dash , R. K., Rogers , A. & Jennings , N. R.2006. Overlapping coalition formation for efficient data fusion in multi-sensor networks. In Proceedings of the 21st National Conference on Artificial Intelligence, 1, 635–640.

    Google Scholar

    Decroos , T., Bransen , L., Van Haaren , J. & Davis , J.2019. Actions speak louder than goals: valuing player actions in soccer. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. ACM, 1851–1861.

    Google Scholar

    De Silva , V., Caine , M. P., Skinner , J., Dogan , S., Kondoz , A., Peter , T., Axtell , E., Birnie , M. & Smith , B.2018. Player tracking data analytics as a tool for physical performance management in football: a case study from Chelsea Football Club Academy. Sports6(4), 130.

    Google Scholar

    Dixon , M. & Coles , S.1997. Modelling association football scores and inefficiencies in the football betting market. Journal of the Royal Statistical Society: Series C (Applied Statistics)46(2), 265–280.

    Google Scholar

    Dixon , M. & Pope , P.2004. The value of statistical forecasts in the UK association football betting market. International Journal of Forecasting20(4), 697–711.

    Google Scholar

    Dixon , M. & Robinson , M.1998. A birth process model for association football matches. Journal of the Royal Statistical Society Series D (The Statistician)47(3), 523–538.

    Google Scholar

    Dobson , S. & Gerrard , B.1999. The determination of player transfer fees in English professional soccer. Journal of Sports Management13(4), 259–279.

    Google Scholar

    Dobson , S., Goddard , J. A. & Dobson , S.2001. The Economics of Football. Cambridge University Press.

    Google Scholar

    Drawer , S. & Fuller , C. W.2002a. An economic framework for assessing the impact of injuries in professional football. Safety Science40(6), 537–556.

    Google Scholar

    Drawer , S. & Fuller , C. W.2002b. Evaluating the level of injury in English professional football using a risk based assessment approach. British Journal of Sports Medicine36(6), 446–451.

    Google Scholar

    Dunis , C. L., Middleton , P. W., Karathanasopolous , A. & Theofilatos , K.2016. Artificial Intelligence in Financial Markets: Cutting Edge Applications for Risk Management, Portfolio Optimization and Economics. Springer.

    Google Scholar

    Ermoliev , Y. M. & Wets , R. B.1988. Numerical Techniques for Stochastic Optimization. Springer- Verlag.

    Google Scholar

    Fang , F., Stone , P. & Tambe , M.2015. When security games go green: designing defender strategies to prevent poaching and illegal fishing. In Proceedings of the 24th International Conference on Artificial Intelligence, 2589–2595.

    Google Scholar

    Farzindar , A. & Inkpen , D.2015. Natural language processing for social media. Synthesis Lectures on Human Language Technologies8(2), 1–166.

    Google Scholar

    Felsen , P. & Lucey , P.2017. “Body Shots” : analyzing shooting styles in the NBA using Body Pose. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2017/02/1690.pdf.

    Google Scholar

    Fernández , J. & Bornn , L.2019. Decomposing the immeasurable sport: a deep learning expected possession value framework for soccer. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2019/02/Decomposing-the-Immeasurable-Sport.pdf.

    Google Scholar

    Fister Jr, I., Ljubic , K., Suganthan , P. N., Perc , M. & Fister , I.2015. Computational intelligence in sports: challenges and opportunities within a new research domain. Applied Mathematics and Computation262, 178–186.

    Google Scholar

    Fuller , C. W.2018. Modeling the impact of players’ workload on the injury-burden of English Premier League football clubs. Scandinavian Journal of Medicine and Science in Sports28(6), 1715–1721.

    Google Scholar

    Ganguly , S. & Frank , N.2018. The problem with win probability. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/2011.pdf.

    Google Scholar

    Gardiner , C.2009. Stochastic Methods. Springer.

    Google Scholar

    Gelman , A., Carlin , J., Stern , H., Dunson , D., Vehtari , A. & Rubin , D.2004. Bayesian Data Analysis. Chapman and Hall/CRC.

    Google Scholar

    Glickman , M. E. & Stern , H. S.1996. A state-space model for National Football League scores. Journal of the American Statistical Association93, 25–35.

    Google Scholar

    Goel , S., Pennock , D. M., Reeves , D. M. & Yu , C.2008. Yoopick: a combinatorial sports prediction market. In Twenty-Third AAAI Conference on Artificial Intelligence.

    Google Scholar

    Graham , I. & Stott , H.2008. Predicting bookmaker odds and efficiency for UK football. Applied Economics40(1), 99–109.

    Google Scholar

    Hägglund , M., Waldén , M. & Ekstrand , J.2006. Previous injury as a risk factor for injury in elite football: a prospective study over two consecutive seasons. British Journal of Sports Medicine40(9), 767–772.

    Google Scholar

    Hägglund , M., Waldén , M. & Ekstrand , J.2009. Injury incidence and injury patterns in professional football: the UEFA injury study. British Journal of Sports Medicine45(7), 553–558.

    Google Scholar

    Hägglund , M., Waldén , M. & Ekstrand , J.2013. Fewer ligament injuries but no preventive effect on muscle injuries and severe injuries: an 11-year follow-up of the UEFA Champions League injury study. British Journal of Sports Medicine47(12), 732–737.

    Google Scholar

    Hanson , R. D.2007. Logarithmic market scoring rules for modular combinatorial information aggregation. Journal of Prediction Markets1, 1–15.

    Google Scholar

    Harville , D.1976. The use of linear-model methodology to rate high school or college football teams. Journal of the American Statistical Association72(358), 278–289.

    Google Scholar

    Harville , D.1980. Predictions for National Football League games via linear-model methodology. Journal of the American Statistical Association75(371), 516–524.

    Google Scholar

    Haugh , M. B. & Singal , R.2018. How to play strategically in fantasy sports (and win). In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/1001.pdf.

    Google Scholar

    Hendricks , W., DeBrock , L. & Koenker , R.2003. Uncertainty, hiring, and subsequent performance: the NFL draft. Journal of Labor Economics21(4), 857–886.

    Google Scholar

    Hobbs , J., Power , P., Sha , L., Ruiz , H. & Lucey , P.2018. Quantifying the value of transitions in soccer via spatiotemporal trajectory clustering. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/2008.pdf.

    Google Scholar

    Hochreiter , S. & Schmidhuber , J.1997. Long short-term memory. Neural Computation9(8), 1735–1780.

    Google Scholar

    Hucaljuk , J. & Rakipović , A.2011. Predicting football scores using machine learning techniques. In Proceedings of the 34th International Convention MIPRO.

    Google Scholar

    Hullin , B. T., Gabbett , T. J., Lawson , D. W., Caputi , P. & Sampson , J. A.2016. The acute:chronic workload ratio predicts injury: high chronic workload may decrease injury risk in elite rugby league players. British Journal of Sports Medicine50(4), 231–236.

    Google Scholar

    Jayalath , K. P.2018. A machine learning approach to analyze ODI cricket predictors. Journal of Sports Analytics4(1), 73–84.

    Google Scholar

    Jayantha , S. B., Anthony , A., Abhilashab , G., Shaikb , N. & Srinivasaa , G.2018. A team recommendation system and outcome prediction for the game of cricket. Journal of Sports Analytics4(1), 263–273.

    Google Scholar

    Joseph , A., Fenton , N. & Neil , M.2006. Predicting football results using Bayesian nets and other machine learning techniques. Knowledge-Based Systems19(7), 544–553.

    Google Scholar

    Kaluarachchi , A. and Aparna , S. V.2011. CricAI: a classification based tool to predict the outcome in ODI cricket. In Fifth International Conference on Information and Automation for Sustainability, 250–255.

    Google Scholar

    Karlis , D. & Ntzoufras , I.2008. Bayesian modelling of football outcomes: using the Skellam’s distribution for the goal difference. IMA Journal of Management Mathematics20(2), 133–145.

    Google Scholar

    Kelly , D., Coughlan , G. F., Green , B. S. & Caulfield , B.2012. Automatic detection of collisions in elite level rugby union using a wearable sensing device. Sports Engineering15(2), 81–92.

    Google Scholar

    Kolodner , J.2014. Case-Based Reasoning. Morgan Kaufmann.

    Google Scholar

    Korte , B. & Vygen , J.2012. The Knapsack Problem. InCombinatorial Optimization. Springer, 459–470.

    Google Scholar

    Landers , J. R. & Duperrouzel , B.2018. Machine learning approaches to competing in fantasy leagues for the NFL. IEEE Transactions on Games. 11(2), 159–172

    Google Scholar

    Le , H. M., Carr , P., Yue , Y. & Lucey , P.2017a. Data-driven ghosting using deep imitation learning. In: MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2017/02/1671-2.pdf.

    Google Scholar

    Le , H. M., Yue , Y., Carr , P. & Lucey , P.2017b. Coordinated multi-agent imitation learning. In Proceedings of the 34th International Conference on Machine Learning-Volume, 70, 1995–2003.

    Google Scholar

    le Gall , F., Carling , C., Williams , M. & Reilly , T.2010. Anthropometric and fitness characteristics of international, professional and amateur male graduate soccer players from an elite youth academy. Journal of Science and Medicine in Sport13(1), 90–95.

    Google Scholar

    Lehtokangas , M., Saarinen , J., Kaski , K. & Huuhtanen , P.1995. Initializing weights of a multilayer perceptron network by using the orthogonal least squares algorithm. Neural Computation7(5), 982–999.

    Google Scholar

    Leung , C. K. & Joseph , K. W.2014. Sports data mining: predicting results for the college football games. Procedia Computer Science35, 710–719.

    Google Scholar

    Lucey , P., Bialkowski , A., Carr , P., Foote , E. & Matthews , I. A.2012. Characterizing multi-agent team behavior from partial team tracings: evidence from the English Premier League. In Twenty-Sixth AAAI Conference on Artificial Intelligence.

    Google Scholar

    Lysens , R., Steverlynck , A., van den Auweele , Y., Lefevre , J., Renson , L., Claessens , A. & Ostyn , M.1984. The predictability of sports injuries. Sports Medicine1(1), 6–10.

    Google Scholar

    Maher , M. J.1982. Modelling association football scores. Statistica Neerlandica36(3), 109–118.

    Google Scholar

    Manning , C. D. & Schütze , H.1999. Foundations of Statistical Natural Language Processing. MIT Press.

    Google Scholar

    Masethe , H. D. & Masethe , M. A.2014. Prediction of heart disease using classification algorithms. In Proceedings of the world Congress on Engineering and computer Science, 2, 22–24.

    Google Scholar

    Matthews , T., Ramchurn , S. D. & Chalkiadakis , G.2012. Competing with humans at fantasy football: team formation in large partially-observable domains. In Twenty-Sixth AAAI Conference on Artificial Intelligence, 1394–1400.

    Google Scholar

    McCabe , A.2002. An artificially intelligent sports tipper. In Australian Joint Conference on Artificial Intelligence, 2557, 718–718.

    Google Scholar

    McCabe , A. & Trevathan , J.2008. Artificial intelligence in sports prediction. In Fifth International Conference on Information Technology: New Generations (itng 2008).

    Google Scholar

    McHale , I. & Relton , S.2018. Identifying key players in soccer teams using network analysis and pass difficulty. European Journal of Operational Research268(1), 339–347.

    Google Scholar

    McHale , I. & Scarf , P.2011. Modelling the dependence of goals scored by opposing teams in international soccer matches. Statistical Modelling11(3), 219–236.

    Google Scholar

    Nelsen , R. B.2006. An Introduction to Copulas. Springer.

    Google Scholar

    Pak , A. & Paroubek , P.2010. Twitter as a corpus for sentiment analysis and opinion mining. In LREC, 10, 1320–1326.

    Google Scholar

    Pan , S. J. & Yang , Q.2010. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering22(10), 1345–1359.

    Google Scholar

    Pan , X., Han , C. S., Dauber , K. & Law , K. H.2007. A multi-agent based framework for the simulation of human and social behaviors during emergency evacuations. AI and Society22(2), 113–132.

    Google Scholar

    Pang , B. & Lee , L.2008. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval2(1–2), 1–135.

    Google Scholar

    Podlog , L., Buhler , C. F., Pollack , H., Hopkins , F. N. & Burgess , P. R.2015. Time trends for injuries and illness, and their relation to performance in the National Basketball Association. Journal of Science and Medicine in Sports18(3), 278–282.

    Google Scholar

    Power , P., Cherukumudi , A., Ganguly , S., Wei , F., Sha , L., Hobbs , J., Ruiz , H. & Lucey , P.2019. Trading places – simulating goalkeeper performance using spatial & body-pose data. In https://statsweb-wpengine.netdna-ssl.com/wp-content/uploads/2019/03/Trading-Places_website.pdf.

    Google Scholar

    Power , P., Hobbs , J., Ruiz , H., Wei , Z. & Lucey , P.2018. Mythbusting set-pieces in soccer. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/2007.pdf.

    Google Scholar

    Power , P., Ruiz , H., Wei , Z. & Lucey , P.2016. Not all passes are created equal: objectively measuring the risk and reward of passes in soccer from tracking data. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1605–1613.

    Google Scholar

    Price , R. J., Hawkins , R. D., Hulse , M. A. & Hodson , A.2004. The Football Association medical research programme: an audit of injuries in academy youth football. British Journal of Sports Medicine38(4), 466–471.

    Google Scholar

    Prokhorenkova , L., Gusev , G., Vorobev , A., Dorogush , A. V. & Gulin , A.2018. CatBoost: unbiased boosting with categorical features. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 6638–6648.

    Google Scholar

    Ramchurn , S. D., Polukarov , M., Farinelli , A., Jennings , N. R. & Truong , C.2010. Coalition formation with spatial and temporal constraints. In Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, 3, 1181–1188.

    Google Scholar

    Ramchurn , S. D., Rogers , A., Macarthur , K., Farinelli , A., Vytelingum , P., Vetsikas , I. & Jennings , N. R.2008. Agent-based coordination technologies in disaster management. In Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems: Demo Papers. International Foundation for Autonomous Agents and Multiagent Systems, 1651–1652.

    Google Scholar

    Ramchurn , S. D., Simpson , E., Fischer , J., Huynh , T. D., Ikuno , Y., Reece , S., Jiang , W., Wu , F., Flann , J., Roberts , S. J., Moreau , L., Rodden , T. & Jennings , N. R.2016. A disaster response system based on human-agent collectives. Journal of Artificial Intelligence Research57, 661–708.

    Google Scholar

    Ramchurn , S. D., Wu , F., Fischer , J., Reece , S., Jiang , W., Roberts , S. J., Rodden , T. & Jennings , N. R.2015. Human-agent collaboration for disaster response. Journal of Autonomous Agents and Multi-Agent Systems30, 82–111.

    Google Scholar

    Richmond , J.1974. Estimating the efficiency of production. International Economic Review15(2), 515–21.

    Google Scholar

    Rue , H. & Salvesen , O.2000. Prediction and retrospective analysis of soccer matches in a league. Journal of the Royal Statistical Society. Series D (The Statistician)49(3), 399–418.

    Google Scholar

    Schapire , R. E.2003. The Boosting Approach to Machine Learning: An Overview. Springer, 149–171.

    Google Scholar

    Sebastiani , F.2002. Machine learning in automated text categorization. ACM Computing Surveys (CSUR)34(1), 1–47.

    Google Scholar

    Seidl , T., Cherukumudi , A., Hartnett , A., Carr , P. & Lucey , P.2018. Bhostgusters: realtime interactive play sketching with synthesized NBA defenses. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2018/02/1006.pdf.

    Google Scholar

    Shi , Z., Moorthy , S. & Zimmermann , A.2013. Predicting NCAAB match outcomes using ML techniques – some results and lessons learned. In MLSA@PKDD/ECML, Sports Analytics Workshop.

    Google Scholar

    Simpson , E., Roberts , S., Psorakis , I. & Smith , A.2013. Dynamic Bayesian combination of multiple imperfect classifiers. In Decision Making and Imperfection. Springer, 1–35.

    Google Scholar

    Sinha , A., Fang , F., An , B., Kiekintveld , C. & Tambe , M.2018. Stackelberg security games: looking beyond a decade of success. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, 5494–5501.

    Google Scholar

    Skellam , J. G.1948. A probability distribution derived from the binomial distribution by regarding the probability of success as variable between the sets of trials. Journal of the Royal Statistical Society. Series B (Methodological)10(2), 257–261.

    Google Scholar

    Srinivas , K., Rani , B. K. & Govrdhan , A.2010. Applications of data mining techniques in healthcare and prediction of heart attacks. International Journal on Computer Science and Engineering (IJCSE)2(02), 250–255.

    Google Scholar

    Stekler , H. O., Sendor , D. & Verlander , R.2010. Issues in sports forecasting. International Journal of Forecasting26(3), 606–621.

    Google Scholar

    Sugar , G. & Swenson , T.2015. Predicting optimal game day fantasy football teams. In http://cs229.stanford.edu/proj2015/115_report.pdf.

    Google Scholar

    Suziki , A. K., Salasar , L. E. B., Leite , J. G. & Louzada-Neto , F.2009. A Bayesian approach for predicting match outcomes: the 2006 (Association) Football World Cup. Journal of the Operational Research Society61(10), 1530–1539.

    Google Scholar

    Swartz , T. B.2018. Where should i publish my sports paper?The American Statistician, 1–6.

    Google Scholar

    Tran-Thanh , L., Stein , S., Rogers , A. & Jennings , N. R.2014. Efficient crowdsourcing of unknown experts using bounded multiarmed bandits. Artificial Intelligence214, 89–111.

    Google Scholar

    Vilar , L., Araújo , D., Davids , K. & Bar-Yam , Y.2013. Science of winning soccer: emergent pattern-forming dynamics in association football. Journal of Systems Science and Complexity26(1), 73–84.

    Google Scholar

    Vytelingum , P., Ramchurn , S. D., Voice , T., Rogers , A. & Jennings , N. R.2011. Agent-based modeling of smart-grid market operations. In 2011 IEEE Power and Energy Society General Meeting, 1–8.

    Google Scholar

    Wang , K. C. & Zemel , R.2016. Classifying NBA offensive plays using neural networks. In MIT Sloan Sports Analytics Conference. http://www.sloansportsconference.com/wp-content/uploads/2016/02/1536-Classifying-NBA-Offensive-Plays-Using-Neural-Networks.pdf.

    Google Scholar

    Ward , P., Tankovich , M., Ramsden , J. S., Drust , B. & Bornn , L.2018. Volume and intensity are important training related factors in injury incidence in American Football Athletes. In MIT Sloan Sports Analytics Conference. http://www.lukebornn.com/papers/ward_ssac_2018.pdf.

    Google Scholar

    Whitaker , G. A., Silva , R. & Edwards , D.2017. A Bayesian inference approach for determining player abilities in soccer. Big Data6(4), 271–290.

    Google Scholar

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

    Google Scholar

    Yue , Y., Lucey , P., Carr , P., Bialkowski , A. & Matthews , I.2014. Learning fine-grained spatial models for dynamic sports play prediction. In IEEE International Conference on Data Mining, 670–679.

    Google Scholar

    Zak , T., Huang , C. & Siegfried , J.1979. Production efficiency: the case of professional basketball. The Journal of Business52(3), 379–392.

    Google Scholar

    Zelič , I., Kononenko , I., Lavrač , N. & Vuga , V.1997. Induction of decision trees and Bayesian classification applied to diagnosis of sport injuries. Journal of Medical Systems21(6), 429–444.

    Google Scholar

    Zheng , S., Yue , Y. & Hobbs , J.2016. Generating long-term trajectories using deep hierarchical networks. In Advances in Neural Information Processing Systems 29, 1543–1551.

    Google Scholar

  • Cite this article

    Ryan Beal, Timothy J. Norman, Sarvapali D. Ramchurn. 2019. Artificial intelligence for team sports: a survey. The Knowledge Engineering Review 34(1), doi: 10.1017/S0269888919000225
    Ryan Beal, Timothy J. Norman, Sarvapali D. Ramchurn. 2019. Artificial intelligence for team sports: a survey. The Knowledge Engineering Review 34(1), doi: 10.1017/S0269888919000225
    shu
Download PDF

Article Metrics

Article views(40) PDF downloads(111)

Other Articles By Authors

REVIEW   Open Access    

Artificial intelligence for team sports: a survey

  • Received: 14 June 2019
  • Revised: 12 November 2019
  • Accepted: 16 November 2019
  • Published online: 20 December 2019
The Knowledge Engineering Review  34,  2019, 34(1)  |  Cite this article

Abstract: Abstract: The sports domain presents a number of significant computational challenges for artificial intelligence (AI) and machine learning (ML). In this paper, we explore the techniques that have been applied to the challenges within team sports thus far. We focus on a number of different areas, namely match outcome prediction, tactical decision making, player investments, fantasy sports, and injury prediction. By assessing the work in these areas, we explore how AI is used to predict match outcomes and to help sports teams improve their strategic and tactical decision making. In particular, we describe the main directions in which research efforts have been focused to date. This highlights not only a number of strengths but also weaknesses of the models and techniques that have been employed. Finally, we discuss the research questions that exist in order to further the use of AI and ML in team sports.

    HTML

    Acknowledgments

    • We would like to thank Dr. Tim Matthews and Mr. Ramm Mylvagananam for their expert advice and comments while writing this paper. This research is sponsored by the EPSRC NPIF doctoral training grant number EP/S515590/1.

    • https://www.plunkettresearch.com/statistics/Industry-Statistics-Sports-Industry-Statistic-and-Market-Size-Overview.

    • https://www.forbes.com/sites/bernardmarr/2015/03/25/big-data-the-winning-formula-in-sports/#467bd87d34de.

    • https://www.optasports.com.

    • https://www.stats.com.

    • https://www.telegraph.co.uk/football/2016/05/28/play-off-final-how-much-is-premier-league-promotion-really-worth/.

    • https://www.businessinsider.com/inside-story-star-lizard-tony-bloom-2016-2?r=US&IR=T.

    • https://www.bbc.co.uk/news/business-44362134.

    • https://www.draftkings.co.uk.

    • https://www.fanduel.com.

    • https://fantasy.premierleague.com.

    • https://www.jlt.com/our-insights/our-insights/how-injuries-have-affected-the-english-premier-league.

    • Score frequency data sourced from Anderson and Sally (2014).

    • Market data sourced from—https://www.atkearney.com/communications-media-technology/article?/a/the-sports-market.

    • Referred to as American Football throughout, not to be confused with Association Football.

    • Special teams are units that are on the field during kicking plays.

    • https://www.vox.com/2015/1/21/7866121/deflated-football-patriots-cheating.

    • Try—placing the ball down in a given zone at the end of the oppositions.

    • A drop-goal is scored when a player kicks the ball from hand through the opposition’s posts.

    • Scrum—a method of restarting play that involves players packing closely together with their heads down and attempting to gain possession of the ball.

    • https://www.ruck.co.uk/rugby-positions-roles-beginners/.

    • Baseball was the first sport to really see the power of data. In the 1970s, Bill James began writing an annual ‘Baseball Abstract’, containing statistics he collected by hand. This inspired the Oakland A’s and Billy Beane (their General Manager) to change the way they operate by using data to make key decisions. This is documented in the book ‘Moneyball’ by Micheal Lewis. There are many statistics collected in Baseball and the professional teams are much more advanced at using data in comparison to other sports.

    • Odds that are given across the whole of the past season (2016/2017) with historic average odds (from a number of the top bookmakers) and results data taken from https://www.oddsportal.com.

    • Where inefficiency in the match outcome betting market will be indicated if returns are greater than the return on an uninformed random betting strategy.

    • These ratings are a measure of strength based on head-to-head results and quality of opponent.

    • Other metrics = historic power indexes, Pythagorean wins, offensive strategy (pass_attempts/rush_attempts), and turnover differential.

    • https://www.complex.com/sports/2015/01/how-betting-lines-work/.

    • https://www.uefa.com/uefachampionsleague/about/.

    • A similar but different sport to Rugby Union.

    • http://www.toptipper.com.

    • Pick’em is a game within Fantasy leagues where competitors guess who will win each American Football game in the NFL game that game week.

    • In a draft, teams take turns selecting from a pool of eligible players, usually from a college or high school system.

    • American youth players come through a college and draft system rather than individual teams having youth teams.

    • https://www.stats.com/sportvu-basketball/.

    • Overloading the opposition when they have just lost the ball.

    • This study was run over the 2016/2017 EPL season.

    • http://www.forbes.com/the-70-billion-fantasy-football-market.

    • Rules: https://fantasy.premierleague.com/a/help.

    • When a team concedes no goals.

    • The amount of points needed to break even is set to 111.21.

    • Success rate = number of weeks that the model would earn a profit.

    • A common method for calculating workload is by multiplying the athletes perceived exertion (sRPE) by session duration (e.g., if an athlete reports an sRPE of 5 and trained for 90 minutes, the athlete’s workload for the day would be 450 arbitrary units (AU)).

    • Note that football focused on domestic league games.

    • A form of logical inference which starts with an observation or set of observations then seeks to find the simplest and most likely explanation for the observations.

    Rights and permissions
    • © Cambridge University Press, 20192019Cambridge University Press
References (129)
  • About this article
    Cite this article
    Ryan Beal, Timothy J. Norman, Sarvapali D. Ramchurn. 2019. Artificial intelligence for team sports: a survey. The Knowledge Engineering Review 34(1), doi: 10.1017/S0269888919000225
    Ryan Beal, Timothy J. Norman, Sarvapali D. Ramchurn. 2019. Artificial intelligence for team sports: a survey. The Knowledge Engineering Review 34(1), doi: 10.1017/S0269888919000225
    shu

    • Catalog

      /

      DownLoad:  Full-Size Img  PowerPoint
      Return
      Return