Dynamic Bayesian forecasting models of football match outcomes with estimation of the evolution variance parameter

Owen, Alun

doi:10.1093/imaman/dpq018

Cited by 32 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Applications of time-series models to football were published by Knorr-Held (2000), Crowder et al (2002) and Owen (2011). Glickman and Stern (1998), Stefani (2009) and Percy (2011a) considered American football, rugby and Alpine skiing, respectively, while Urban (2012) and Cattelan et al (2013) considered basketball.…”

Section: Time Seriesmentioning

confidence: 99%

“…This sequential updating algorithm is particularly useful for interactive dynamic learning while sporting competitions are in progress. Its use for 'within-game' analysis is relatively new, though Glickman and Stern (1998), Knorr-Held (2000), Crowder et al (2002) and Owen (2011) considered applications to 'between-game' situations. Furthermore, Congdon (2003) presented an accessible account of Bayesian inference for several dynamic models, including the time-series models that we review and apply here.…”

Section: Dynamic Learningmentioning

confidence: 99%

See 1 more Smart Citation

Strategy selection and outcome prediction in sport using dynamic learning for stochastic processes

Percy

2015

Journal of the Operational Research Society

View full text Add to dashboard Cite

Stochastic processes are natural models for the progression of many individual and team sports. Such models have been applied successfully to select strategies and to predict outcomes in the context of games, tournaments and leagues. This information is useful to participants and gamblers, who often need to make decisions while the sports are in progress. In order to apply these models, much of the published research uses parameters estimated from historical data, thereby ignoring the uncertainty of the parameter values and the most relevant information that arises during competition. In this paper, we investigate candidate stochastic processes for familiar sporting applications that include cricket, football and badminton, reviewing existing models and offering some new suggestions. We then consider how to model parameter uncertainty with prior and posterior distributions, how to update these distributions dynamically during competition and how to use these results to make optimal decisions. Finally, we combine these ideas in a case study aimed at predicting the winners of next year's University Boat Race.

show abstract

Section: Time Seriesmentioning

confidence: 99%

Section: Dynamic Learningmentioning

confidence: 99%

Strategy selection and outcome prediction in sport using dynamic learning for stochastic processes

Percy

2015

Journal of the Operational Research Society

View full text Add to dashboard Cite

show abstract

“…Segundo os autores, muitos requisitos devem ser considerados para a montagem de um cronograma, que, além de justo com todas as equipes, deve levar em consideração os interesses comerciais das emissoras de televisão e administradores dos estádios. Com a mesma preocupação e intenção tem-se os trabalhos de Owen (2011), que intitula a sua metodologia de "Dynamic Generalized Linear Models" (DGLMs) e propõe uma agenda para o Campeonato Inglês. E Ribeiro e Urrutia (2012) também realizam a mesma análise, propondo combinações para as séries "A" e "B" do futebol brasileiro.…”

Section: Breve Visão Do Campo Do Futebol Dentro Da Administraçãounclassified

Futebol Paixão ou Negócios? Uma Análise da Produção Científica Mundial

Andrade¹,

Ramos²

2015

PODIUM

View full text Add to dashboard Cite

A cientificidade em torno do futebol vem ganhando destaque no meio acadêmico. Mas o assunto é abordado sob distintas perspectivas: paixão, fato social, que pode ser compreendido e estudado dentro da área de conhecimento das Ciências Sociais e na área de negócios, mais especificamente envolvendo a área de Administração. O objetivo deste trabalho é verificar, por meio de um estudo bibliométrico, como o esporte vem sendo estudado no mundo nos últimos cinco anos (paixão ou negócio?), buscando compreender, além da área mais relevante, quais assuntos vêm se destacando nesse campo. Os resultados apontaram que, quantitativamente, o esporte vem sendo mais estudado por meio de abordagens ligadas às Ciências Sociais do que à Administração. No entanto, a diversidade de temas verificados nos artigos não possibilita afirmar que um ou outro assunto, dentro dessas grandes áreas, vem sendo tratado com maior destaque no período pesquisado. Palavras-chave: Futebol; Paixão; Fato Social; Negócios; Administração. FOOTBALL: PASSION OR BUSINESS? AN ANALYSIS OF THE WORLDWIDE SCIENTIFIC ABSTRACTThe scientific around football has been gaining attention in academia. But the subject is approached from different perspectives: passion, social fact, which can be understood and studied within the area of knowledge of the social sciences and business area, specifically involving the administration area. The aim of this study was to verify through a bibliometric study how football has been approached in the world in recent years. The results showed that, quantitatively, the sport has been most studied through approaches of Social Sciences of the Administration. However, the diversity of subjects verified in Articles state that does not allow either subject, within these broad areas, is being addressed with more emphasis in the period surveyed.

show abstract

“…Nonetheless, estimation remains a problem because teams' strengths evolve over time-some teams improve, others decline. Owen (2011) and Koopman and Lit (2015) model this strength evolution. McHale and Kharrat (BBC Sport, 2017) take a different approach, using player line-ups to determine the strengths.…”

Section: Introductionmentioning

confidence: 99%

Football scores, the Poisson distribution and 30 years of final year projects in Mathematics, Statistics and Operational Research

Scarf

2017

MSOR

View full text Add to dashboard Cite

The development of the Poisson match as a model used in the prediction of the outcome of football matches is described. In this context, many interesting modelling projects arise that are suitable for undergraduate, final year students. In a narrative that discusses the author's engagement with this model and other related models, the paper presents a number of these projects, their attractions and their pitfalls, and poses a number of questions that are suitable for investigation. The answers to some of these questions would be worthy of the attention of the administrators of their respective sports.

show abstract

Dynamic Bayesian forecasting models of football match outcomes with estimation of the evolution variance parameter

Cited by 32 publications

References 8 publications

Strategy selection and outcome prediction in sport using dynamic learning for stochastic processes

Strategy selection and outcome prediction in sport using dynamic learning for stochastic processes

Futebol Paixão ou Negócios? Uma Análise da Produção Científica Mundial

Football scores, the Poisson distribution and 30 years of final year projects in Mathematics, Statistics and Operational Research

Contact Info

Product

Resources

About