In line with our coverage of predictive analytics and the world cup, we’ve been looking at interesting technologies that have been used to predict the winner of this years tournament. Everyone from Goldman Sachs to Stehpen Hawking has been involved — albeit relatively unsuccessfully — and it was revealed recently that Microsoft has also attempted something similar.
Although it has received relatively little media coverage, Cortana, Microsoft’s artificially intelligent voice system, enjoyed an incredible World Cup this year, having successfully predicted the winner of nearly every game after the group stages.
Cortana used Microsoft’s Bing search engine to 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. Moreover, the programme also accounted for other factors that could play a significant role in a game such as home field advantage (for Brazil), playing surface (hybrid grass), and game-time weather conditions.
According to Craig Beilinson, Microsoft’s director of consumer communications:
“The elimination round has been magical for us here as we watch all of these predictions come true,” Beilinson says. “It’s been a fun computer science experience here and we think a lot about where we can take it. We hope it’s fun for people to see more than just search results, to see more information that they can follow.”
Interestingly, Microsoft’s Cortana “knocked off” some “presumptive heavyweights”, including the popular polling aggregation website FiveThirtyEight. While FiveThirtyEight predicted Brazil to win in its game against Germany, for example, Cortana gave the edge to the World Cup winners.
Google also entered the predictive analytics scene during the world cup and saw some success too, with an accuracy of 92.86. The differences between Microsoft and Google however was that Cortana’s model relied “’more on what betting markets are saying, whereas Google’s is an “inductive model derived from game-play data’”
“Normally, sports playoffs do not actually update the predictions that much,” David Rothschild, a Microsoft researcher and economist, explained before the World Cup began. “There is a long regular season, and the way a team plays in any given game of the playoffs is not providing too much new, meaningful information. That is not the case in the World Cup, which lacks a regular season, so each match tells me a lot, and the long duration of the event means I am making serious updates after every match, not to mention during the match.”
Read more here
Interested in more content like this? Sign up to our newsletter, and you wont miss a thing!
(Image credit: Calcio Streaming)