How smart can smartphones get? Intelligent enough to predict where you’ll be tomorrow at this time.
A team of researchers at the University of Birmingham in the UK have developed an algorithm that can capture your movement patterns, as well as those of other people in your social group. Armed with that information, the algorithm can then predict — to an accuracy of around 20 meters — where you’ll be 24 hours from now.
“In a world dominated by social networks and always-connected mobile devices, the potential applications of our study are many, in particular for marketing, advertising, and personalized services,” said Manlio De Domenico, who took part in the research. “If a system is able to predict with reasonable accuracy where the user is directed, it could provide geo-localized and personalized recommendations based on his or her future movement. For example, a user might receive meal offers related to restaurants in the area they are moving towards.”
Another potential use is in law enforcement, where the algorithm could be used to help predict the future location of crimes.
The team’s research won the Nokia Mobile Data Open Challenge, which required participants to find ways to analyze “big data” from around 200 cellphone users over the course of a year.
“In order to predict movements of people accurately, this study leverages their synchronicity and correlation,” said Antonio Lima, a PhD student at the university’s school of computer science. “For example, friends John and Emily usually have lunch together … at a Chinese restaurant close to John’s office. Sometimes, though, they like to go a little farther to a nice Italian restaurant. When Emily is heading to the Italian place, this algorithm uses this information to predict that John is very likely to go there soon as well.”
The team now aims to build a platform to enable the development of third-party mobile apps using the algorithm.