Predicting the results of sport matches and competitions is a growing research field, benefiting from the increasing amount of available data and novel data analytics techniques. Excellent forecasts can be achieved by advanced statistical and machine learning methods applied to detailed historical data, especially in very popular sports such as football (soccer). Here, we show that despite the large number of confounding factors, the results of a football team in longer competitions (e.g., a national league) follow a basically linear trend that is also useful for predictive purposes. In support of this claim, we present a set of experiments of linear regression compared to alternative approaches on a database collecting the yearly results of 746 teams playing in 22 divisions spanning up to five different levels from 11 countries, in 25 football seasons, for a total of 181,160 matches grouped in 9386 seasonal time series.
Get full access to this article
View all access options for this article.
References
1.
González-VallejoC, PhillipsN. Predicting soccer matches: A reassessment of the benefit of unconscious thinking. Judgm Decis Mak, 2010; 5:200–206.
2.
DobsonS, GoddardJ.The economics of football. Cambridge, United Kingdom; Cambridge University Press, 2011.
3.
HaghighatM, RastegariH, NourafzaN. A review of data mining techniques for result prediction in sports. ACSIJ, 2013; 2:7–12.
4.
WessonJ.The science of soccer. Boca Raton, FL: CRC Press, 2002.
5.
CrowderM, DixonM, LedfordA, et al.Dynamic modelling and prediction of English Football League matches for betting. J R Stat Soc Series D Statistician, 2002; 51:157–168.
GoddardJ, AsimakopoulosI. Forecasting football results and the efficiency of fixed-odds betting. J Forecast, 2004; 23:51–66.
8.
LangsethH.Beating the bookie: A look at statistical models for prediction of football matches. In: Proceedings of the 12th Scandinavian Conference on Artificial Intelligence. Bristol, United Kingdom: IOP Press, 2013, pp. 165–174.
9.
SheridanD. Modelling football match results and testing the efficiency of the betting market. Master's thesis, National University of Ireland, Maynooth, Ireland, 2012.
GoddardJ.Regression models for forecasting goals and match results in association football. Int J Forecast, 2005; 21:331–340.
26.
HeuerA, RubnerO.Towards the perfect prediction of soccer matches. ArXiv 1207.4561.
27.
HeuerA, RubnerO. Optimizing the prediction process: from statistical concepts to the case study of soccer. PLoS One, 2014; 9:e10464–7.
28.
MartinsRG, MartinsAS, NevesLA, et al.Exploring polynomial classifier to predict match results in football championships. Expert Syst Appl, 2017; 83:79–93.
29.
PrasetioD, HarliliD.Predicting football match results with logistic regression. In Proceedings of the International Conference On Advanced Informatics: Concepts, Theory And Application (ICAICTA 2016), 2016, pp. 1–5.
30.
RochaE, Figueiredo FilhoD, ParanhosR, et al.How can soccer improve statistical learning?. Int J Innov Educ Res, 2014; 2:83–87.
31.
SnyderJ. What actually wins soccer matches: Prediction of the 2011–2012 Premier League for fun and profit. Master's thesis, Princeton University, NJ, 2013.
BååthR. Modeling match results in soccer using a hierarchical Bayesian Poisson Model. Technical Report LUCS minor 18, Lund University Cognitive Science, Lund, Sweden, 2015.
34.
BaioG, BlangiardoM. Bayesian hierarchical model for the prediction of football results. J Appl Stat, 2010; 37:253–264.
35.
BoldrinB. Predicting the result of English Premier League soccer games with the use of Poisson models. Master's thesis, Stetson University, DeLand, FL, 2017.
HeuerA, RubnerO. How does the past of a soccer match influence its future? Concepts and statistical analysis. PLoS One, 2012; 7:e4767–8.
39.
LindeJ, LøkketangenM. Predicting outcomes of association football matches based on individual players' performance. Master thesis, Norwegian University of Science and Technology, Trondheim, Norway, 2014.
40.
LouzadaF, SuzukiA, SalasarL. Predicting match outcomes in the English Premier League: Which will be the final rank?. J Data Sci, 2014; 12:235–254.
41.
RazaliN, MustaphaA, YatimFA, et al.Predicting football matches results using Bayesian networks for English Premier League (EPL). IOP Conf Ser Mater Sci Eng, 2017; 226:01209–9.
van WijkN. Soccer analytics. Predicting the outcome of soccer matches. Master's thesis, VU University Amsterdam, Amsterdam, The Netherlands, 2012.
44.
BoshnakovG, KharratT, McHaleI. A bivariate Weibull count model for forecasting association football scores. Int J Forecast, 2017; 33:458–466.
45.
KharratT. A journey across football modelling with application to algorithmic trading. PhD thesis, School of Mathematics, University of Manchester, Manchester, United Kingdom, 2016.
ConstantinouA, FentonN.Improving predictive accuracy using smart-data: The case of football teams' evolving performance. In: Proceedings of the 13th UAI Bayesian Modeling Applications Workshop (BMAW 2016). New York, 2016, pp. 54–55.
54.
CuiT, LiJ, WoodwardJ, et al. An ensemble based genetic programming system to predict English Football Premier League games. In: Proceedings of the IEEE Conference on Evolving and Adaptive Intelligent Systems (EAIS 2013), 2013, pp. 138–143.
55.
EggelsH, van ElkR, PechenizkiyM. Explaining soccer match outcomes with goal scoring opportunities predictive analytics. In: Proceedings of Machine Learning and Data Mining for Sports Analytics, ECML/PKDD 2016 Workshop, 2016, Riva del Garda, Italy.
HoekstraV. Predicting football results with an evolutionary ensemble classifier. Master's thesis, VU University Amsterdam, Amsterdam, The Netherlands, 2012.
MinB, ChoeC, EomH, et al.A compound framework for sports results prediction: A football case study. Knowl-Based Syst, 2008; 21:551–562.
60.
OwramipurF, EskandarianP, MoznebF. Football result prediction with Bayesian network in Spanish League-Barcelona Team. Int J Comput Theory Eng, 2013; 5.
61.
Trindade TavaresA. Predicting results of Brazilian soccer league matches. Technical report, University of Wisconsin–Madison, Madison, WI, 2013.
62.
UlmerB, FernandezM. Predicting soccer match results in the English Premier League. Technical report, Stanford University, Stanford, CA, 2014.
BunkerR, ThabtahF. A machine learning framework for sport result prediction. Appl Comput Informat, 2019; 15:27–33.
66.
KočišJ. Soccer results prediction using neural networks. Master's thesis, Technical University of Košice, Slovak Republic, 2016.
67.
PettersonD, NyquistR. Football match prediction using deep learning: Recurrent neural network applications. Master's thesis, Chalmers University of Technology, Gothenburg, Sweden, 2017.
68.
ClementeF, CouceiroM, MartinsF, et al.Using network metrics in soccer: a macro-analysis. J Hum Kinet, 2015; 45:123–134.
69.
GrundT.Network structure and team performance: The case of English Premier League soccer teams. Soc Netw, 2012; 34:682–690.
70.
HeuerA, RubnerO. Fitness, chance, and myths: an objective view on soccer results. Eur Phys J B, 2009; 67:445–458.
71.
López PeñaJ, TouchetteH. A network theory analysis of football strategies. ArXiv 1206.6904.
72.
ConstantinouA, FentonN. Determining the level of ability of football teams by dynamic ratings based on the relative discrepancies in scores between adversaries. J Quant Anal Sports, 2013; 9:37–50.
73.
PappalardoL, CintiaP. Quantifying the relation between performance and success in soccer. ArXiv 1705.00885.
74.
PappalardoL, CintiaP, FerraginaP.et al. PlayeRank: Multi-dimensional and role-aware rating of soccer player performance. ArXiv 1802.04987.
75.
BrownA, RambaccussingD, ReadeJ, et al.Forecasting with social media: Evidence from tweets on soccer matches. Econ Inq, 2017; 56:1748–1763.
76.
KampakisS, AdamidesA. Using Twitter to predict football outcomes. ArXiv 1411.1243.
77.
BrockwellP, DavisR. Introduction to time series and forecasting. New York: Springer, 2016.
78.
HyndmanR, KoehlerA, OrdJ, et al.Forecasting with exponential smoothing: The state space approach. Berlin, Germany: Springer, 2008.
79.
HamiltonHH.An extension of the Pythagorean expectation for association football. J Quant Anal Sports, 2011; 7:Article-15.
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
