Home Finance Goldman Sachs used Machine Learning to Determine World Cup Outcomes & Gets...

Goldman Sachs used Machine Learning to Determine World Cup Outcomes & Gets a Clear Winner

Artificial intelligence is undeniably taking the world by storm. It has penetrated different fields or aspects of life including finance, healthcare, military, and research among others with the aim of providing efficient, fast and accurate services or products.

If the recent move by Goldman Sachs is anything to go by, then the firm may have found a way to use artificial intelligence in sports, particularly in predicting the eagerly-anticipated 2018 FIFA World Cup outcomes.

According to Lionel Messi, a renowned Argentine football superstar, elegance and talent in football translate to nothing without both precision and rigor. This is a statement that Goldman Sachs appears to have taken to heart in efforts of coming up with a forecast for the much-awaited 2018 FIFA World Cup.

Goldman Sachs leveraged machine learning in running 200,000 models as well as mining data on the individual player and team attributes in a bid to compile its predictions for specific match results during the sport’s event of the year. Subsequently, the firm simulated one million variations of the competition in a bid to compute the chances of advancement for the individual squads.

The tournament bracket outlined below displays how Goldman Sachs expects the World Cup to unfold. Also, keep in mind that the numbers noted next to each country, which show whether it will beat its opponent, show the forecasted, unrounded number of goals scored in every possible iteration of the event. The numbers were obtained based on machine-learning outcomes that were applied to numerous scenarios.

Strategists included in the Goldman’s international research team said in a client note that, they are highly interested in machine learning models, as they can go through a large volume of potential explanatory variables to generate predictions that are more accurate than traditional alternatives. Below are some of the key takeaways from the firm’s data:

  • Brazil is not new to World Cup victory. In fact, data from Goldman Sach’s suggest that the country will win its sixth title in the popular tournament through beating Germany in the final match with an unrounded score of 1.70 to 1.41.
  • Although France has better chances of taking the World Cup trophy as opposed to Germany, its anticipated match with five-time World Cup champions Brazil in the semifinals will not go in its favor. Instead, the derby will see the country fall short of tournament’s final or title match.
  • Even though England is anticipated to reach the quarterfinals, Goldman Sachs claims the team will lose to Germany.
  • Both Argentina and Spain are predicted to underperform, particularly by losing in the quarterfinal stage.
  • Despite being the World Cup host, Russia will lose at the group stage.
  • Saudi Arabia is seen as the surprise team that will break out of the group stage ahead of Russia.

Despite all the predictions made by Goldman Sachs, football or soccer is an unpredictable sport with too many variables at play than what Goldman Sachs can evaluate. With that in mind, the team authors of the report said that they capture the stochastic nature of the World Cup through advanced statistical techniques and considers numerous details in their work. However, the predictions remain largely uncertain, due to the unpredictable nature of the game.

Source BusinessInsider

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...