Combining machine learning and human experts to predict match outcomes in football: A baseline model
Combining machine learning and human experts to predict match outcomes in football: A baseline model
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
Artificial Intelligence, Natural Language Processing
Beal, Ryan James
d9874cb0-bd92-4a16-8576-78d769b41ff7
Middleton, Stuart
404b62ba-d77e-476b-9775-32645b04473f
Norman, Timothy
663e522f-807c-4569-9201-dc141c8eb50d
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3
2 February 2021
Beal, Ryan James
d9874cb0-bd92-4a16-8576-78d769b41ff7
Middleton, Stuart
404b62ba-d77e-476b-9775-32645b04473f
Norman, Timothy
663e522f-807c-4569-9201-dc141c8eb50d
Ramchurn, Sarvapali
1d62ae2a-a498-444e-912d-a6082d3aaea3
Beal, Ryan James, Middleton, Stuart, Norman, Timothy and Ramchurn, Sarvapali
(2021)
Combining machine learning and human experts to predict match outcomes in football: A baseline model.
The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence, , Virtual.
02 - 09 Feb 2021.
5 pp
.
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper, we present a new application-focused benchmark dataset and results from a set of baseline Natural Language Processing and Machine Learning models for prediction of match outcomes for games of football (soccer). By doing so we give a baseline for the prediction accuracy that can be achieved exploiting both statistical match data and contextual articles from human sports journalists. Our dataset is focuses on a representative time-period over 6 seasons of the English Premier League, and includes newspaper match previews from The Guardian. The models presented in this paper achieve an accuracy of 63.18% showing a 6.9% boost on the traditional statistical methods.
Text
IAAI_Football_Paper-CameraReady
- Accepted Manuscript
More information
Accepted/In Press date: 1 December 2020
Published date: 2 February 2021
Venue - Dates:
The Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence, , Virtual, 2021-02-02 - 2021-02-09
Keywords:
Artificial Intelligence, Natural Language Processing
Identifiers
Local EPrints ID: 445607
URI: http://eprints.soton.ac.uk/id/eprint/445607
PURE UUID: b92a1ec5-0330-4f90-9c7c-67910257eba6
Catalogue record
Date deposited: 18 Dec 2020 17:30
Last modified: 17 Mar 2024 06:09
Export record
Contributors
Author:
Ryan James Beal
Author:
Sarvapali Ramchurn
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics