Combining Machine Learning and Human Experts to Predict Match Outcomes in Football: A Baseline Model

TL;DR

This paper introduces a benchmark dataset combining statistical match data and journalistic articles to predict football match outcomes, demonstrating improved accuracy over traditional methods.

Contribution

It provides a new dataset and baseline models that integrate machine learning with human expert insights for football outcome prediction.

Findings

Achieved 63.18% prediction accuracy

Boosted accuracy by 6.9% over traditional methods

Utilized both statistical data and journalistic articles

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.