Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ RUC. Repositorio da ...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 4 versions
addClaim

Aplicación de técnicas estatísticas avanzadas ao baloncesto

Authors: Merino Currás, Uxío Francisco;

Aplicación de técnicas estatísticas avanzadas ao baloncesto

Abstract

[Resumo]: A idea deste traballo é mostrar a utilidade da aplicación de técnicas estatísticas no ámbito do baloncesto, usando diferentes ferramentas para dar solución ás situacións presentadas polo Obradoiro CAB, equipo profesional de baloncesto, a través do seu analista de datos. Todas as bases de datos utilizadas foron cedidas polo propio clube, e conteñen grandes cantidades de información da Liga ACB da tempada actual (2023/24) e a anterior (2022/23), tanto para xogadores (individualmente e agrupados por quintetos en xogo) como para equipos (variables de rendemento dos equipos en cada partido). Partindo destas bases de datos, aplicamos distintas técnicas, cada unha con obxectivos distintos. A nivel individual dos xogadores, aplicaremos un ACP e técnicas de clustering, para resumir a variabilidade dos datos en menos compoñentes, facilitar a representación e etiquetar aos xogadores polo seu estilo de xogo de maneira obxectiva. Para poder optimizar o rendemento, construímos modelos de regresión (lineais e de Machine Learning) cos datos a nivel de equipo e de quintetos para buscar variables relevantes e configuracións de xogadores que dean mellores resultados O deporte é unha rama máis na que o Big Data é decisivo para a toma de decisións estratéxicas e poder obter unha vantaxe competitiva con respecto aos rivais, o que se trata de mostrar neste traballo. O obxectivo global era poder obter unha ferramenta que levase á optimización de xogadores e do seu rendemento, e os resultados obtidos demostran que a aplicación destes métodos axudan en gran medida a lograr isto, transformando os datos en vantaxes.

[Abstract]: The idea of this work is to demonstrate the usefulness of applying statistical techniques in the field of basketball, using different tools to address the situations presented by Obradoiro CAB, a professional basketball team, through its data analyst. All databases used were provided by the club itself and contain large amounts of information from the ACB League for the current season (2023/24) and the previous one (2022/23), both for players (individually and grouped by playing lineups) and for teams (team performance variables in each game). Starting with these databases, various techniques were applied, each with different objectives. At the individual player level, PCA and clustering techniques were used to summarize data variability into fewer components, facilitate representation, and objectively label players by their playing style. To optimize performance, regression models were built (linear and Machine Learning) with team and lineup level data to identify relevant variables and player configurations that yield better results. Sports is another field where Big Data is crucial for strategic decision-making and gaining a competitive edge over rivals, which is what this work aims to demonstrate. The overall objective was to develop a tool that would lead to team optimization and performance improvement. The results obtained show that the application of these methods significantly helps achieve this, transforming data into advantages.

Traballo fin de grao (UDC.FIC). Ciencia e enxeñaría de datos. Curso 2023/2024

Country
Spain
Related Organizations
Keywords

Análise de datos, Modelos de regresión, Aprendizaxe automática, Machine learning, Análise de compoñentes principais, Data analysis, Principal component analysis, Técnicas estatísticas, Statistical techniques, Regression models, Clustering, Random forest

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green