The French national team is the favourite for the upcoming 2024 European Football Championships, while England and Germany also have high hopes of winning the title, according to experts from the Universities of Innsbruck and Luxembourg, Molden University of Applied Sciences and the Technical Universities of Dortmund and Munich.
The European Men's Football Championship (EURO) kicks off in Germany on 14 June 2024. According to the current forecast, France has a 19.2 per cent chance of winning. The research team, consisting of Andreas Groll and Jonas Sternemann (both TU Dortmund University), Gunther Schauberger (TU Munich), Christophe Ley and Florian Felice (both University of Luxembourg), Lars Magnus Hvattum (Molde University of Applied Sciences, Norway) and Achim Zeileis (University of Innsbruck), has created this prediction with the help of machine learning. The forecast combines several statistical models in two steps: In the first step, three complex statistical models are used to determine the strengths of all teams and their players based on different information – including team strenghts based on past matches, a bookmaker model based on betting odds and the ratings of individual players. In the second step, an ensemble of machine learning algorithms decides how best to combine the three models with other information about the teams. Factors such as market value, number of Champions League players and the gross domestic product as a socio-economic factor of the respective country of origin play a role here. “With the help of our model, we can explore the most likely course of the tournament through simulation. It goes without saying that these are only probabilities and that there can be no certainty about the outcome before the tournament,” emphasises Achim Zeileis.
100,000 simulations
The entire Championship was simulated 100,000 times based on the model prediction – match by match, following precisely the tournament draw and taking into account all UEFA rules. This results in probabilities for all teams to progress to the knockout stages and ultimately to win the European Championship. The favourites this time are France with a probability of 19.2 percent, followed by England (16.7 percent), Germany (13.7 percent), Spain (11.4 percent) and Portugal (10.8 percent). The detailed forecast including interactive graphics is linked below. Even though France is considered the favourite, the tournament outcome remains uncertain – even among the top teams, the odds of winning are comparatively low. “Of course, a winning probability of 19.2 per cent also means that France will not become European champions 80.8 per cent of the time,” says Achim Zeileis. Zeileis’ Innsbruck model, which is based on adjusted betting odds and forms part of this extended forecast, has already successfully made predictions in the past, such as correctly predicting the EURO final in 2008 and the World and European champions Spain in 2010 and 2012. This year, it will be used for the third time after the EURO 2020 and the 2022 World Cup as part of a more comprehensive combined model.
Germany in the tournament
Host nation Germany’s chances of winning the tournament are better than the sentiment towards the national team following their elimination in the round of 16 at the last EURO and their preliminary round exit at the 2022 World Cup would suggest, as Andreas Groll explains: “Our model sees Germany definitely making it through the group stage against Switzerland, Scotland and Hungary with 95.2 per cent, while the chances of reaching the final are also comparatively high at 24.6 per cent. And winning the tournament at 13.7 per cent is also not too bad.”
Austria’s chances
After Austria reached the round of 16 at the EURO 2020 held in 2021, expectations are comparatively high this time too: “Austria was drawn into a relatively difficult group, with top favourite France and the Netherlands as another strong team as opponents in the group stage. Our model predicts a probability of 53.4 per cent for Austria to make it to the round of 16, which is not bad considering the group,” emphasises Achim Zeileis. However, further chances are diminishing; according to the forecast, Austria only has a probability of 1.1 per cent of becoming European champions.
Scientific perspective
The EURO 2024 also offers interesting aspects for the researchers from a scientific perspective, as the statisticians are working with detailed data from past tournaments: “We trained the model with data from the last five European Championships and analysed the actual results. This allowed us to refine the weighting of the information sources for Euro 2024,” explains Andreas Groll. The refined model may also be used in future for other forecasts in other areas of research, such as weather forecasts.
Service:
The entire forecast with interactive graphics is available here: https://www.zeileis.org/news/euro2024/
Univ.-Prof. Dr. Achim Zeileis
Department of Statistics
University of Innsbruck
Phone: +43 512 507-70403
Mobile: +43 676 38 48 967
E-Mail: achim.zeileis@uibk.ac.at
Prof. Dr. Andreas Groll
Faculty of Statistics
TU Dortmund University
Phone.: +49 231 755-4229
E-Mail: groll@statistik.tu-dortmund.de
Achim Zeileis, University of Innsbruck
Universität Innsbruck
Universität Innsbruck
Andreas Groll, TU Dortmund University
Roland Baege
Roland Baege
Merkmale dieser Pressemitteilung:
Journalisten, jedermann
Gesellschaft, Mathematik, Wirtschaft
überregional
Buntes aus der Wissenschaft, Forschungsergebnisse
Englisch
Sie können Suchbegriffe mit und, oder und / oder nicht verknüpfen, z. B. Philo nicht logie.
Verknüpfungen können Sie mit Klammern voneinander trennen, z. B. (Philo nicht logie) oder (Psycho und logie).
Zusammenhängende Worte werden als Wortgruppe gesucht, wenn Sie sie in Anführungsstriche setzen, z. B. „Bundesrepublik Deutschland“.
Die Erweiterte Suche können Sie auch nutzen, ohne Suchbegriffe einzugeben. Sie orientiert sich dann an den Kriterien, die Sie ausgewählt haben (z. B. nach dem Land oder dem Sachgebiet).
Haben Sie in einer Kategorie kein Kriterium ausgewählt, wird die gesamte Kategorie durchsucht (z.B. alle Sachgebiete oder alle Länder).