â€œInterdependence and Predictability of Human Mobility and Social Interactionsâ€ by Manlio De Domenico, Antonio Lima, and Mirco Musolesi of the University of Birmingham, UK has been awarded the best entry in the Open category of the Mobile Data Challenge.
In brief, the paper shows how analysis of your mobile phone data correlated with social connections can predict your movements into the next day to a high degree of accuracy.
…we have shown that it is possible to exploit the correlation between movement data and social interactions in order to improve the accuracy of forecasting of the future geographic position of a user. In particular, mobility correlation, measured by means of mutual information, and the presence of social ties can be used to improve movement forecasting by exploiting mobility data of friends. Moreover, this correlation can be used as an indicator of potential existence of physical or distant social interactions and vice versa.
Predictability from mobile data should come as little surprise given that since 2008 a physics research team has suggested they can generate a very high accuracy rate.
Human behavior is 93 percent predictable, a group of leading Northeastern University network scientists recently found. Distinguished Professor of Physics Albert-LÃ¡szlÃ³ BarabÃ¡si and his team studied the mobility patterns of anonymous cell-phone users and concluded that, despite the common perception that our actions are random and unpredictable, human mobility follows surprisingly regular patterns.
The new study, however, suggests that by watching the movements of mobile phones that are related by social network to the target mobile phone that the accuracy of prediction can be even higher. In other words it can even predict the rare variance to a pattern by monitoring relationship influences.
Forbes points out that the new study results were based only on monitoring 25 volunteers in Switzerland but will now be applied to “larger data sets that he will soon be getting from Nokia.”
Malte Spitz: Your phone company is watching