Celebrity Big Data scientist Nate Silver can step aside. And so can Paul the Octopus (anyone remember him?) for that matter. There’s a new god of football predictions in town, and it goes by the name of Cortana. Microsoft’s answer to Siri successfully predicted the outcome of all 15 games of the elimination stage of the FIFA World Cup.

Cortana’s one hundred percent record puts to shame its competitors, which include Mr. Silver of US presidential election fame, who slipped up big time when he pronounced that Brazil would triumph over Germany in the semi-finals. Google also fell foul of the Germans when it predicted France to beat them in the previous round. Here’s the excuse Google gave:

“Perhaps in our excitement about using Cloud Dataflow, BigQuery and Compute Engine to arrive at our predictions, we may have been better served by heeding a more simple truth: Gary Lineker once said, “Football is a simple game: 22 men chase a ball for 90 minutes, and at the end, the Germans always win.”

But there were no slip ups from Cortana, which after hitting 14 out of 14, correctly predicted that Germany would edge Argentina in the final:

Germany will win the Worldcup. 14 predictions correct. #Cortana pic.twitter.com/s2j8HzosdM

— Edd (@EdemXII) July 10, 2014

So how did Microsoft do it? Well, it wasn’t just Cortana alone, it had a lot of help from Bing.

“It’s not really Cortana that makes the predictions,” said Ted Roduner of Microsoft’s Bing division to CMSWire. “It’s Bing. Bing is the soul of Cortana. All of Cortana’s intelligence is built on Bing.”

According to Roduner, Bing is built upon a massive index of data that goes far beyond just indexed websites – images, people, places, things, and all of the data they produce. Bing has a ton of information to dig through.

For Microsoft’s Big Data experts, the guessing game isn’t limited to the World Cup. They’ve tried their luck in all kinds of fields, from determining the top picks in the NBA draft, to guessing the outcome of American Idol, predicting the 2014 Oscars and many more. In the last event, Bing/Cortana successfully picked 21 out of 24 winners.

But the World Cup achievement was something else, not that Microsoft was particulary surprised at its success given how predictive models are becoming increasingly more accurate.

“I approach modeling the World Cup the same I would any other event,” said David Rothschild, an economist at Microsoft, in an interview with Foreign Policy. “The trick is to make a forecast that cuts out subjectivity and lets the data do the talking.”

Microsoft wouldn’t divulge the secret behind it’s algorithm, but put its success down to the waves of data it was able to soak up as the tournament progressed. By the time the group stage had finished, Bing had access to a tsunami of player and team performance data that allowed it to calibrate its model and alter its forecasts for the next round of matches. Other World Cup models continued basing their predictions on pre-tournament data, while Bing was running in real-time.

“A few years ago I would have to wait until each game is over to access all the stats,” said Rothschild. “Now, it is being sent automatically in real time, which makes our models better adjusted and more accurate.”

Microsoft now ranks alongside Big Data legends like SiliconANGLE’s good friend Mr. Silver, and plans to put its analytics capabilities to other uses. “Sports are fun, but we can use the same techniques to predict elections or watch stocks. It’s all about analyzing the raw data,” added Rothschild.

It remains to be seen if Microsoft can keep up this stunning level of accuracy, or if it will fall by the wayside like our friend Nate Silver. But for now at least, this latest success will become yet another compelling argument for those who believe in the power of Big Data.

photo credit: Photocapy via photopin cc