Editor's note

International Internet Magazine. Baltic States news & analytics Sunday, 19.05.2019, 16:04

Artificial intelligence in action: World Cup's champion is predicted

Eugene Eteris, BC, Riga/Copenhagen, 13.06.2018.Print version

The World Cup-2018 kicks off on 14 June, when Russia, the host, plays Saudi Arabia. The field of 32 teams will then gradually be whittled down until a champion is crowned on July 15. Several global banks made their predictions based on "solid" models and research.

The world’s biggest banks have put their quantitative skills to predict the winner.; it has become an exercise to use artificial intelligence for global attention.  The analysis includes several new methods through artificial intelligence, statistical modeling, portfolio theory, and economic analysis.

Information in this rticle are according to columnist Andrew Ross Sorkin and his Times colleagues from DealBook newsletter.

General source: https://www.nytimes.com/2018/06/12/business/dealbook/world-cup-goldman-banks.html?


Swiss prediction

A group from the Swiss bank’s chief investment office scored each team based on an objective skill-level measurement; it is called Elo rating. The method goes through qualification and any home nation advantage;the analysts then is carried out through statistical modeling – so-called Monte Carlo simulation.  

As a result, Germany, Brazil and Spain are most likely to win, with Germany the UBS favorite, with a 24 percent chance of victory.


Goldman Sachs’s prediction

The research team opted to use artificial intelligence algorithms to conduct analysis; the approach is based on the folowing model: The data on team characteristics, individual players and recent team performance was divided into four different types of machine-learning models to analyze the number of goals scored in each match. The models then learn the relationship between these characteristics and goals scored, using the scores of competitive World Cup and European Cup matches since 2005. By cycling through alternative combinations of variables, the model predicted the number of goals scored to determine the winner.

Goldman has predicted a Brazilian victory for the last three World Cups (and has been wrong every time).

ING's prediction

The Dutch bank used a more unusual techniques based on market value of the nation’s team and its previous performance and the assumption that value and success are closely correlated.  According to ING Bank, Spain will be crowned world champion, with a total team value of €1.04 billion ($1.16 billion), with a close second France, which is valued at €1.03 billion.  

Nomura’s prediction

The Japanese bank in its preduction for the tournament's result used the same techniques whish offered balanced risk to investors. In their World Cup winner's analysis they applied "portfolio theory and the efficient markets hypothesis". Nomura looked at the value of players in each team, the momentum of team performance and historical performances of the teams.

The Nomura Bank's analysis suggested that France, Spain and Brazil are the most likely to reach the semifinals, and it predicts that France and Spain will meet in the final.

Bottom line: there are the following favoritesin the World Cup: Germany, Brasil, Spain and France.

Search site