Psychic smartphones? New algorithm could predict where you’ll be tomorrow

If surfing the web on your smartphone has ever made you feel like you're on Star Trek, you're not alone. Today's mobile phones are reminiscent of the tricorder — the fictional hand-held device that could do anything from data analysis to sensor scanning — but its capabilities stopped well short of predicting the future.

We may not be able to say the same for your smartphone.

Researchers at the University of Birmingham in England have reportedly created an algorithm that may soon enable your mobile device to accurately predict where you are going to be.

It sounds like a scene taken from Minority Report, but there's a caveat you may not find as exciting: the algorithm spies on your friends in order to connect the dots.

"To be more precise, not only does it analyze your own mobility patterns, but it also extrapolates from similar data collected from the people in your social circle to identify any divergences from the routine," explains Jan Belezina in a Gizmag report. "The assumption here is that there is a strong correlation between the habits and mobility routines of friends, friends being defined as people who have each other on their contact lists."

So let's say you regularly hit the gym on Thursdays around 7 p.m. On Wednesday night, a standard algorithm could easily assume that's where you'll be in 24 hours time, but this week you've decided to go shopping on Thursday night. The socialized algorithm, after scanning those in your smartphone's contact list, knows that your closest friends are not planning to join you at the mall. And because your shopping has not been dubbed a social activity — as opposed to a party that your friends are planning to attend — the algorithm understands that you're likely to hit the gym as you normally would once you've left the mall.

It's a tough concept to explain, but after conducting experiments on some 200 subjects, researchers found the algorithm could predict where a subject will be in 24 hours time within less than 20 metres. The average margin of error grew to approximately 1 km when the algorithm was stripped of its social component.

"Mirco Musolesi, the head of the team behind the study, points out that the 200 people who were willing to be tracked over an 18-month period may not reflect the general population," reveals Belezina in the Gizmag story. "However, Mirco sees the benefit of the study in that it 'exploited the synchronized rhythm of the city' for enhanced predictive capabilities."

Researchers have obviously spotted the potential of this algorithm, and you can bet mobile networks abroad have taken notice as well. As Belezina mentions, an algorithm capable of accurately predicting a smartphone user's future location could allow such networks to improve tailored advertisements and personalized recommendations to mobile devices.

But such ingenuity is sure to spawn a whole new slate of privacy issues. Just as the plot of Minority Report asked whether a man can be guilty of a crime he has yet to commit, can information pertaining to something you are yet to do still be deemed private?

"However we deal with these kinds of questions, one hopes the algorithm will be used for something more interesting and useful than serving up better targeted ads," shares Belezina. "Dynamic traffic control and clever power distribution grids spring to mind."

(Image from Gizmag)