View all newsletters
Receive our newsletter - data, insights and analysis delivered to you
  1. Technology
  2. Data
June 16, 2014updated 22 Sep 2016 1:25pm

5 analytics tools for predicting World Cup success or failure

You’ll have a better chance than in the office sweepstake.

By Joe Curtis

The World Cup is upon us again, and this time around CBR are prepared.

You see, we’ve compiled a list of algorithms that will help us and you make a safe bet on the winner.

While they range from Microsoft’s search engine to a videogame, all of them feature a deep reliance on data, which probably makes for a more reliable flutter than your mate’s third pint tips.

Microsoft’s Bing

Yes, the search engine is trying to predict the winner of the World Cup. Microsoft said last Tuesday that it’s busy collating lots of data including variables from social to sport to predict every result at the summer football tournament.

Its Bing Predicts feature started by forecasting contestants’ success on TV shows like The Voice, Dancing With the Stars and American Idol, but now a simple search for World Cup Predictions or any group matches will lead to Bing’s predictions.

The team behind it wrote in a blog post: "For the tournament, our models evaluate the strength of each team through a variety of factors such as previous win/loss/tie record in qualification matches and other international competitions and margin of victory in these contests, adjusted for location since home field advantage is a known bias.

"Further adjustments are made related to other factors which give one team advantages over another, such as home field (for Brazil) or proximity (South American teams), playing surface (hybrid grass), game-time weather conditions, and other such factors. In addition, data obtained from prediction markets allows us to tune the win/lose/tie probabilities due to the ‘wisdom of the crowds’ phenomenon captured by the people wagering on the outcomes."

Content from our partners
Rethinking cloud: challenging assumptions, learning lessons
DTX Manchester welcomes leading tech talent from across the region and beyond
The hidden complexities of deploying AI in your business

It reckons the USA is doomed in Group G, garnering zero wins, adding that Germany, with nine points, followed by Portugal’s six, will qualify for the last 16 round.

Winner (of Group G): Germany
Loser (of Group G): USA

Bloomberg

Bloomberg takes a hard-nosed approach to everything, including football. While we’re all busy betting on Argentina, Germany or Brazil because ‘we just have a feeling, you know?’, Bloomberg has aggregated massive amounts of data to make its predictions with confidence with BSports, its analytics service.

That means it gives Brazil a 20.7% chance of winning the World Cup in its own country, followed by Argentina, with 13.7%, and Germany, with 13% chances. England have a rather harsh 2.2% probability, but it’s not as bad as Cameroon’s 0.0%, or even Swuitzerland’s 1% – who’d be willing to have a punt on that?

North Yard Analytics

This analytics firm say their approach to predicting World Cup results is pretty simple. The New York-based company says: "It uses only five explanatory variables, with none based on detailed data about players or teams. It doesn’t know even know who’s going to Brazil and who’s out injured."

After trying it out in 2010 "for a laugh", it surprised its creators by performing quite well, with its predictions for post-tournament FIFA rankings of countries getting it right 59% of the time.

However, the company warns: "We don’t expect any model’s predictions to be 100% accurate in any tournament. Models are designed to have a high success rate in prediction over a large number of tournaments. In other words, a good model might not win a single World Cup betting pool, but it would have more correct predictions than most people over a long series of pools."

So far it’s got it right a surprising number of times for the group stages, with it correctly calling wins for Brazil, Chile and Argentina – but it incorrectly predicted a draw for England against Italy and didn’t see Holland beating Spain, but who did, by a margin of four goals?

Winner: Brazil
Loser (last place in rankings): Korea

TCS SocialSoccer

It might not predict results, but then again you can bet on most things these days. TCS SocialSoccer is a new app from Indian IT services firm Tata, and it collects and analyses social media data to track the mood and thoughts of football fans from around the world.

The app enables real-time analysis of all matches based on Twitter data, where it tracks sentiment, and also uses key talking points from pundits, footballers and fans from across the globe to give you the kind of information usually reserved for the likes of Gary Neville to base your bets on.

You can also follow your favourite teams and compare online conversations about any player.

TCS doesn’t predict the winners and losers itself, but you get to decide based on the information you glean from it.

SAS Visual Analytics

Fittingly, analytics firm SAS has got in on the World Cup action too, feeding data from South Africa’s 2010 competition into its engine to see what correlations it would find.

Employee Anna Brown found no link between a country’s GDP and its World Cup success, but found strong correlations between the number of passes made in a game and a team’s points total and the number of passes and the number of shots made.

Websites in our network
Select and enter your corporate email address Tech Monitor's research, insight and analysis examines the frontiers of digital transformation to help tech leaders navigate the future. Our Changelog newsletter delivers our best work to your inbox every week.
  • CIO
  • CTO
  • CISO
  • CSO
  • CFO
  • CDO
  • CEO
  • Architect Founder
  • MD
  • Director
  • Manager
  • Other
Visit our privacy policy for more information about our services, how Progressive Media Investments may use, process and share your personal data, including information on your rights in respect of your personal data and how you can unsubscribe from future marketing communications. Our services are intended for corporate subscribers and you warrant that the email address submitted is your corporate email address.
THANK YOU