Making the cut: forecasting non impact injuries in professional soccer

This paper proposes a methodology to predict work in non-traumatic injuries in professional soccer players. The task to be solved is a classification problem of the player's status with a window of 72 hours. The data set used corresponds to records of complete training by the players of Belgran...

Descripción completa

Detalles Bibliográficos
Autor principal: Cicognini, Agustín
Otros Autores: Roccatagliata, Pablo
Formato: Tesis de maestría acceptedVersion
Lenguaje:Inglés
Publicado: 2023
Materias:
Fútbol
Football
Soccer
Análisis de datos
Predicción tecnológica
Data Analysis
Non-traumatic injury
Machine Learning
Survival analysis
SHAP
Acceso en línea:https://repositorio.utdt.edu/handle/20.500.13098/11567
Aporte de:
Repositorio Digital Universidad Torcuato Di Tella de Universidad Torcuato Di Tella
id I57-R163-20.500.13098-11567
record_format dspace
institution Universidad Torcuato Di Tella
institution_str I-57
repository_str R-163
collection Repositorio Digital Universidad Torcuato Di Tella
language Inglés
orig_language_str_mv eng
topic Fútbol
Football
Soccer
Análisis de datos
Predicción tecnológica
Data Analysis
Non-traumatic injury
Machine Learning
Survival analysis
SHAP
spellingShingle Fútbol
Football
Soccer
Análisis de datos
Predicción tecnológica
Data Analysis
Non-traumatic injury
Machine Learning
Survival analysis
SHAP
Cicognini, Agustín
Making the cut: forecasting non impact injuries in professional soccer
topic_facet Fútbol
Football
Soccer
Análisis de datos
Predicción tecnológica
Data Analysis
Non-traumatic injury
Machine Learning
Survival analysis
SHAP
description This paper proposes a methodology to predict work in non-traumatic injuries in professional soccer players. The task to be solved is a classification problem of the player's status with a window of 72 hours. The data set used corresponds to records of complete training by the players of Belgrano de Córdoba professional soccer team of the first division of Argentina. The chosen model is GBM with an AUC of 0.7. Interpretation exercises based on SHAP are performed on the chosen model to analyze the characteristics that determine the model's predictions. In addition, possible extensions are proposed such as the use of the results of the model at the time of contractual negotiation given the estimated proportion of time that the player will spend outside due to injury and the economic cost of those absences given, at least, by the direct salary cost of that player. Another approach to the injury forecasting problem based on survival time models is also discussed.
author2 Roccatagliata, Pablo
author_facet Roccatagliata, Pablo
Cicognini, Agustín
format Tesis de maestría
acceptedVersion
author Cicognini, Agustín
author_sort Cicognini, Agustín
title Making the cut: forecasting non impact injuries in professional soccer
title_short Making the cut: forecasting non impact injuries in professional soccer
title_full Making the cut: forecasting non impact injuries in professional soccer
title_fullStr Making the cut: forecasting non impact injuries in professional soccer
title_full_unstemmed Making the cut: forecasting non impact injuries in professional soccer
title_sort making the cut: forecasting non impact injuries in professional soccer
publishDate 2023
url https://repositorio.utdt.edu/handle/20.500.13098/11567
work_keys_str_mv AT cicogniniagustin makingthecutforecastingnonimpactinjuriesinprofessionalsoccer
bdutipo_str Repositorios
_version_ 1764820542563549185

Ejemplares similares