So far in the World Cup knockout stages, Microsoft’s Bing search engine has been perfect in predicting the winners. Since Microsoft added the so-called prediction engine to its Cortana virtual assistant for Windows phones on June 28th, it’s gone 12 for 12, as chronicled by an ebullient series of tweets curated by Cortana program manager Marcus Ash:
Bing is looking like the Paul the Octopus of the 2014 World Cup. Brazil must be desperately hoping that streak comes to an end today—Bing is narrowly forecasting that Germany will beat the host country.
Here’s how Microsoft describes the Bing prediction model:
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.
The model draws heavily on the work of Microsoft researcher and economist David Rothschild, who has made a number of other accurate predictions in everything from elections to the Academy Awards.
If Bing’s streak continues, we’ll see an Argentina-Germany final, a matchup that has some history behind it. Argentina won a 1986 matchup with West Germany, then lost the rematch in 1990.