Using machine learning in Football

Bc. Thomas Stvarnik

Diplomová práce

Abstract:

This thesis explores the application of machine learning techniques to football data analysis, focusing on the history, use cases, and implementation of these methods in the sport. The study begins with a literature review, tracing the development of data analysis in football from early beginnings with Charles Reep to the modern age, and discussing the role of event data in the sport. The thesis then delves into the history, types, and workflow of machine learning, with emphasis on supervised, unsupervised, semi-supervised, and reinforcement learning. The practical part of the study is dedicated to the implementation of a machine learning model, specifically the training process and utilization of the final selected model to create a shot map. This implementation relies on Python, XGBoost, Pandas, and Matplotlib technologies. The thesis outlines the intents, workspace configuration, and training data features, before describing the model training algorithm and methods for finding the best results. The study offers valuable insights into the potential of machine learning applications in football data analysis, and enhancing understanding of the game.

Keywords

Machine Learning, Data analysis, Event data, Python, xGboost, Football, xG

Jazyk práce: angličtina

Datum vytvoření / odevzdání či podání práce: 3. 4. 2023

Obhajoba závěrečné práce

• Obhajoba proběhla 23. 5. 2023
• Vedoucí: Ing. Petr Hanzlík, Ph.D.
• Oponent: Ondřej Gojda, Ph.D.

Česká zemědělská univerzita v Praze

Provozně ekonomická fakulta

Magisterský studijní program:
Informatics