Modeling of Football Match Outcomes with Expected Goals Statistic
Keywords:sports analytics, expected goals, predictive modeling, data science, probabilistic model
Aim. Our research examined the predictive capabilities of mathematical models that are solely based on the expected goal statistics obtained from a publicly available database.
Method. We collected match and expected goals data for 310 matches from three European Leagues (Bundesliga, La Liga, and Serie A). We created three probabilistic models based on the expected goals statistic and compared them with two well-established probabilistic models using binomial deviance, squared error, and profitability in the betting market as evaluation metrics.
Results. Our best model adjusted the expected goal statistics for homefield advantage and outperformed the two probabilistic models used for comparison. Two of our models were profitable under certain betting conditions.
Limitations. Our models explored a simplistic integration of expected goals into a Poisson based probabilistic model and did not include other contributing factors such as a team’s defensive prowess. The number of games simulated was also limited due to the premature closure of the European Leagues due to the COVID-19 pandemic.
Conclusions. The use of a probabilistic model based solely on expected goals score statistic can provide some meaningful insight into forecasting the outcome of a football match and can develop useful betting strategies.
How to Cite
Copyright (c) 2021 Adan Partida, Anastasia Martinez, Cody Durrer, Oscar Gutierrez, Filippo Posta
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The copyright holder for this article has granted JSR a license to display the article in perpetuity.