Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms

Peter Hassard; Dermot Kerr

doi:10.1109/ISSC61953.2024.10603147

Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms

Peter Hassard, Dermot Kerr

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

388 Downloads (Pure)

Abstract

This paper demonstrates how supervised machine learning algorithms can be leveraged to predict match outcomes from 2015/16 football season for matches in the top professional leagues of 5 countries (Spain - La Liga, England - Premier League, Italy - Serie A, Germany - 1. Bundesliga and France - Ligue 1). In the summer of 2023 StatsBomb released this free data; once important features on game play activity are generated and processed. A clear correlation between the match outcome and the location of a team's events on the pitch will be shown, moreover the ability to predict a match outcome based on the team's previous matches, this was done using their mean values for relevant features. For optimal prediction levels, the machine learning models in this paper had their hyperparameters selectively adjusted.

Original language	English
Title of host publication	Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024
Editors	Huiru Zheng, Ian Cleland, Adrian Moore, Haiying Wang, David Glass, Joe Rafferty, Raymond Bond, Jonathan Wallace
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	6
ISBN (Electronic)	9798350352986
DOIs	https://doi.org/10.1109/ISSC61953.2024.10603147
Publication status	Published (in print/issue) - 14 Jun 2024
Event	35th Irish Systems and Signals Conference, ISSC 2024 - Belfast, United Kingdom Duration: 13 Jun 2024 → 14 Jun 2024

Publication series

Name	Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

Conference

Conference	35th Irish Systems and Signals Conference, ISSC 2024
Country/Territory	United Kingdom
City	Belfast
Period	13/06/24 → 14/06/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

Machine Learning
StatsBomb
XGBoost

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ISSC61953.2024.10603147

Predicting_football_match_outcomesAuthor Accepted Manuscript, 1.44 MB
2024156785Final published version, 601 KB

Cite this

Hassard, P., & Kerr, D. (2024). Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms. In H. Zheng, I. Cleland, A. Moore, H. Wang, D. Glass, J. Rafferty, R. Bond, & J. Wallace (Eds.), Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024 (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISSC61953.2024.10603147

Hassard, Peter ; Kerr, Dermot. / Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms. Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. editor / Huiru Zheng ; Ian Cleland ; Adrian Moore ; Haiying Wang ; David Glass ; Joe Rafferty ; Raymond Bond ; Jonathan Wallace. Institute of Electrical and Electronics Engineers Inc., 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024).

@inproceedings{382e96cd66174171bb3289b7f2a20e17,

title = "Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms",

abstract = "This paper demonstrates how supervised machine learning algorithms can be leveraged to predict match outcomes from 2015/16 football season for matches in the top professional leagues of 5 countries (Spain - La Liga, England - Premier League, Italy - Serie A, Germany - 1. Bundesliga and France - Ligue 1). In the summer of 2023 StatsBomb released this free data; once important features on game play activity are generated and processed. A clear correlation between the match outcome and the location of a team's events on the pitch will be shown, moreover the ability to predict a match outcome based on the team's previous matches, this was done using their mean values for relevant features. For optimal prediction levels, the machine learning models in this paper had their hyperparameters selectively adjusted.",

keywords = "Machine Learning, StatsBomb, XGBoost",

author = "Peter Hassard and Dermot Kerr",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 35th Irish Systems and Signals Conference, ISSC 2024 ; Conference date: 13-06-2024 Through 14-06-2024",

year = "2024",

month = jun,

day = "14",

doi = "10.1109/ISSC61953.2024.10603147",

language = "English",

series = "Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Huiru Zheng and Ian Cleland and Adrian Moore and Haiying Wang and David Glass and Joe Rafferty and Raymond Bond and Jonathan Wallace",

booktitle = "Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024",

address = "United States",

}

Hassard, P & Kerr, D 2024, Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms. in H Zheng, I Cleland, A Moore, H Wang, D Glass, J Rafferty, R Bond & J Wallace (eds), Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024, Institute of Electrical and Electronics Engineers Inc., 35th Irish Systems and Signals Conference, ISSC 2024, Belfast, United Kingdom, 13/06/24. https://doi.org/10.1109/ISSC61953.2024.10603147

Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms. / Hassard, Peter; Kerr, Dermot.
Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. ed. / Huiru Zheng; Ian Cleland; Adrian Moore; Haiying Wang; David Glass; Joe Rafferty; Raymond Bond; Jonathan Wallace. Institute of Electrical and Electronics Engineers Inc., 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms

AU - Hassard, Peter

AU - Kerr, Dermot

PY - 2024/6/14

Y1 - 2024/6/14

N2 - This paper demonstrates how supervised machine learning algorithms can be leveraged to predict match outcomes from 2015/16 football season for matches in the top professional leagues of 5 countries (Spain - La Liga, England - Premier League, Italy - Serie A, Germany - 1. Bundesliga and France - Ligue 1). In the summer of 2023 StatsBomb released this free data; once important features on game play activity are generated and processed. A clear correlation between the match outcome and the location of a team's events on the pitch will be shown, moreover the ability to predict a match outcome based on the team's previous matches, this was done using their mean values for relevant features. For optimal prediction levels, the machine learning models in this paper had their hyperparameters selectively adjusted.

AB - This paper demonstrates how supervised machine learning algorithms can be leveraged to predict match outcomes from 2015/16 football season for matches in the top professional leagues of 5 countries (Spain - La Liga, England - Premier League, Italy - Serie A, Germany - 1. Bundesliga and France - Ligue 1). In the summer of 2023 StatsBomb released this free data; once important features on game play activity are generated and processed. A clear correlation between the match outcome and the location of a team's events on the pitch will be shown, moreover the ability to predict a match outcome based on the team's previous matches, this was done using their mean values for relevant features. For optimal prediction levels, the machine learning models in this paper had their hyperparameters selectively adjusted.

KW - Machine Learning

KW - StatsBomb

KW - XGBoost

UR - http://www.scopus.com/inward/record.url?scp=85201144977&partnerID=8YFLogxK

U2 - 10.1109/ISSC61953.2024.10603147

DO - 10.1109/ISSC61953.2024.10603147

M3 - Conference contribution

AN - SCOPUS:85201144977

T3 - Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

BT - Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024

A2 - Zheng, Huiru

A2 - Cleland, Ian

A2 - Moore, Adrian

A2 - Wang, Haiying

A2 - Glass, David

A2 - Rafferty, Joe

A2 - Bond, Raymond

A2 - Wallace, Jonathan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 35th Irish Systems and Signals Conference, ISSC 2024

Y2 - 13 June 2024 through 14 June 2024

ER -

Hassard P, Kerr D. Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms. In Zheng H, Cleland I, Moore A, Wang H, Glass D, Rafferty J, Bond R, Wallace J, editors, Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024. Institute of Electrical and Electronics Engineers Inc. 2024. (Proceedings of the 35th Irish Systems and Signals Conference, ISSC 2024). doi: 10.1109/ISSC61953.2024.10603147

Predicting Football Match Outcomes Using Event Data and Machine Learning Algorithms

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this