Next place prediction algorithms are invaluable tools, capable of increasing the efficiency of a wide variety of tasks, ranging from reducing the spreading of diseases to better resource management in areas such as urban planning and communication networks. In this work we estimate upper and lower limits on the predictability of human mobility to help assess the performance of competing algorithms. We do this using GPS traces from 604 individuals participating in a multiyear long experiment, The Copenhagen Networks study. Earlier works, focusing on the prediction of a participants whereabouts in the next time bin, have found very high upper limits (> 90%). We show that these upper limits, at least for some spatiotemporal scales, are mainly driven by the fact that humans tend to stay in the same place for long periods of time. This leads us to propose a new approach, focusing on the prediction of the next Point of Interest. By removing the trivial parts of human mobility behaviour, we show that the predictability of human mobility is significantly lower than implied by earlier works.
From A to B: A new approach to the limits of predictability of human mobility patterns
Edin Lind Ikanovic, Anders Mollgaard