Home Geospatial Applications LBS Now, smartphones can predict user’s future location

Now, smartphones can predict user’s future location

UK: UK researchers have developed an algorithm that can predict a person’s future geographic location using data gathered from their friends’ smartphones. In the study of two hundred people, the algorithm predicted the location of some users 24 hours later within 100 metres, others as close as 20 metres.

Mirco Musolesi, lead researcher and computer science lecturer at the University of Birmingham, said the algorithm is exploiting the synchronised rhythm of the city. “There is a problem for privacy, it is a big problem for these kind of services in general,” said Musolesi. Still, if users’ phone information could be protected, the algorithm has a potential future in targeted advertising, said Musolesi.

The algorithm predicted user’s movements by comparing their data with people in their social group. For example, if Bob usually goes to the gym on Tuesday, but instead does an errand, the algorithm will look to his friends, Jack and Joe. If Jack and Joe are doing their normal routine, the algorithm will, probably correctly, predict Bob will continue on to the gym, his normal routine, following his errand.
“The mutual information between these two patterns is very high,” said Musolesi. “The movement of friends is highly co-ordinated.”

The Birmingham group won 3,000 euros for their work, part of a Nokia-sponsored Mobile Data Challenge, which gave a winning team an opportunity to analyse smart phone data —location, communication patterns and app usage— collected from 200 volunteers over the course of 18 months.

Edoardo Airoldi, assistant professor of statistics at Harvard University, said the “next big thing” in big data is to study human behaviour on a large scale.

“Up to two or three years ago there was so much missing information. Someone could produce some interesting, intriguing research, but it would just be intriguing, not convincing from a scientific standard,” said Airoldi.

Now that almost everyone uses a cell phone, the data is more robust, he said. “If you can track most people then the results are convincing instead of intriguing,” he said.

Source: The Star