| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 4.13 MB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
Com a globalização do desporto e a crescente importância atribuída à análise de dados
recolhidos durante o jogo, a avaliação do desempenho individual e coletivo no futebol tornouse
uma prática comum. No entanto, esta análise frequentemente carece do uso de ferramentas
baseadas em aprendizagem automática (ML).
Nesse sentido, esta dissertação explora o uso de técnicas de ML e pretende alcançar dois
objetivos principais. O primeiro consiste na resolução de um problema de regressão, destinado
a prever a eficácia dos remates do jogador com base em indicadores de desempenho como a
sua posição, os minutos jogados, o total de remates e os golos marcados. O segundo visa
resolver um problema de classificação, que classifique os níveis de desempenho do jogador com
base na eficácia dos seus remates.
Para ambas as tarefas, foram examinados e comparados vários métodos de aprendizagem
automática; a Árvore de Decisão e o Gradient Boosting foram considerados os mais eficazes.
Estes modelos demonstraram resultados superiores na previsão da eficácia dos jogadores e na
classificação do seu desempenho, oferecendo uma nova abordagem à análise do futebol que
vai para além da análise estatística convencional.
With the globalization of sport and the growing importance attached to the analysis of data collected during the game, the evaluation of individual and collective performance in soccer has become common practice. However, this analysis often lacks the use of tools based on machine learning (ML). This dissertation explores the use of ML techniques and aims to achieve two main objectives. The first is to solve a regression problem aimed at predicting the effectiveness of a player's shots based on performance indicators, such as position, minutes played, total shots and goals scored. The second aims to solve a classification problem, which classifies the player's performance levels based on the effectiveness of their shots. For both tasks, various machine learning methods were examined and compared; Decision Tree and Gradient Boosting were found to be the most effective. These models demonstrated superior results in predicting players' effectiveness and classifying their performance, offering a new approach to soccer analysis that goes beyond conventional statistical analysis.
With the globalization of sport and the growing importance attached to the analysis of data collected during the game, the evaluation of individual and collective performance in soccer has become common practice. However, this analysis often lacks the use of tools based on machine learning (ML). This dissertation explores the use of ML techniques and aims to achieve two main objectives. The first is to solve a regression problem aimed at predicting the effectiveness of a player's shots based on performance indicators, such as position, minutes played, total shots and goals scored. The second aims to solve a classification problem, which classifies the player's performance levels based on the effectiveness of their shots. For both tasks, various machine learning methods were examined and compared; Decision Tree and Gradient Boosting were found to be the most effective. These models demonstrated superior results in predicting players' effectiveness and classifying their performance, offering a new approach to soccer analysis that goes beyond conventional statistical analysis.
Description
Keywords
Machine learning Football Soccer Regression models Classification models GoalRatio Player's performance Decision tree Gradient boosting Aprendizagem automática Futebol Modelos de regressão Modelos de classificação Árvore de decisão Desempenho do jogador