Lev Yashin, one of the greatest goalkeepers in the history of football, believed that unpredictability is the beauty of the game. It certainly is. Soccer has the power to keep millions of nail-biting spectators around the world on the edge of their chairs.
Nonetheless, the 2014 FIFA World Cup was considered to be one of the easiest games to predict--especially the final between the mighty Germany and the Messi-led Argentina. One of the popular phrases that was doing rounds in the social media space was "head says Germany, but heart says Argentina."
The last six time that Germany and Argentina have come face-to-face in world cups, Germany has lost just once--in the 1986 final. The last time the countries met in the 1990 World Cup, Germany had beaten Argentina for the same 1-0 score. Despite all this, the final game played at Maracana remained beautifully unpredictable, till Germany's Mario Goetze shook the net and shattered Argentina's world cup dreams at the 113th minute.
It was pure logic that made such guesswork possible this time. Team Germany had all the right ingredients for success--a strong and confident team, tactical intelligence, world-class strikers and some very important historical data.
But still, prediction, is not an easy job. Our friends from the animal kingdom, like Paul the octopus and Nelly the elephant, have predicted the champions with unbelievable accuracy. But our friends from the tech world can't really rely on sixth sense for predictions. They instead relied on data.
While many companies, including Google and Apple, tried to predict the winners of world cup this year, the clear winner among predictors this time was Microsoft and its Cortana digital assistant. With its most recent prediction of Germany as the world cup champion, Cortana got 15 out of 16 predictions right in the knock-out round. The only time it went wrong was while predicting the outcome of losers' final between Brazil and Netherland.
Cortana is the flagship feature of Windows Phone 8.1, the latest version of Microsoft's windows phone operating system. Microsoft used the same 'prediction engine' to deliver results through its Bing search engine too. The underlying technology is the same, confirms a Microsoft spokesman in his email to PC World US. "Cortana is using the same algorithms as Bing uses, although it's not quite clear if Bing has tweaked its algorithms since the group stage."
A post on Bing Blogs, dated June 11, says, "Starting today, if you search for "World Cup Predictions", or any group matches (both preliminary as well as later in the single elimination rounds) we will display the chances of each respective team to win."
The predictions, delivered in its Bing search engine results, and through its Cortana virtual assistant on Windows phones, are part of a broader effort to give people not just relevant search results, but information about things that interest them. This would keep them coming back to Bing, according to Craig Beilinson, Microsoft's director of consumer communications, reports Quartz.
According to its official blog , here is what Bing did to ensure its predictions were accurate:
"The process of predicting outcomes of sporting events is unlike voting show predictions, as popularity and some sentiment signals do not play similar roles in determining who wins a contest. Rather, the actions and performances of a handful of individuals solely determine who wins, loses, or ties.
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."
David Rothschild, a Microsoft researcher and economist, and the master-mind behind the technology, relies heavily on prediction-market data. He successfully predicted 2012 U.S. presidential election, the 2013 and 2014 Academy Awards, and, recently, India's general election too. He would probably be able to forecast many more events.
But alas, football may no longer be unpredictable!