EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
3488. A Neural Network Approach to Evaluate Expected Goals in Football
Invited abstract in session TC-16: Football analytics, stream OR in Sports.
Tuesday, 12:30-14:00Room: 19 (building: 116)
Authors (first author is the speaker)
| 1. | Giuseppina Dello Ioio
|
| Department of Economic and Legal Studies, University of Naples Parthenope | |
| 2. | Stefania Corsaro
|
| University of Naples Parthenope | |
| 3. | Zelda Marino
|
| University of Naples Parthenope |
Abstract
The sports industry has a significant global reach, with a value of $480 billion in 2023, which is expected to increase to $629.81 billion by 2028. These data reveal various profit potentials, particularly for the betting industry, which generated a total turnover of €1.41 trillion in 2022, of which €730 billion was attributed to football alone. Due to its predominant role in the global sporting landscape and its significant economic impact, this work focuses on football, specifically on Expected Goals (xG). The accuracy of predicting xG plays a critical role in the financial and strategic decisions of football teams, as well as for investors and bookmakers, as it allows them to assess a team’s performance and identify value bets more accurately. This work proposes an innovative Neural Network approach to predict Expected Goals in the main Italian league, Serie A, with the aim to provide a significant advancement in the application of predictive methods to football, opening new perspectives for analyzing and optimizing sporting and financial performance. Implementing this methodology could improve on-field performance and optimize team investments. Additionally, it could provide important insights for investors and bookmakers, enabling them to make more informed and profitable decisions in the context of professional football. This work is part of a larger research project that aims to evaluate financial contracts indexed to the performance of professional athletes.
Keywords
- Forecasting
- Machine Learning
Status: accepted
Back to the list of papers