Predictability in Human Mobility : Interpretability, Extensions and Applications

Overview & Synopsis

Predicting mobility-related behavior is an important yet challenging task. On one hand, factors such as one's routine or preferences for a few favorite locations may help in predicting their mobility. On the other hand, several contextual factors, such as variations in individual preferences, weather, traffic, or even a person's social contacts, can affect mobility patterns and make its prediction significantly more challenging.A fundamental approach to study mobility-related behavior is to assess how predictable such behavior is, deriving theoretical limits on the accuracy that a prediction model can achieve given a specific dataset. This approach focuses on the inherent nature and fundamental patterns of human behavior captured in that dataset, filtering out factors that depend on the specificities of the prediction method adopted.However, the current state-of-the-art method to estimate predictability in human mobility, proposed by Song et al., suffers from three major limitations. First, it has low explainability, which makes it difficult to trace the causes of given predictability values. Second, it views one's mobility as one monolithic entity, thus preventing us from understanding the impact of one's routine on predictability. And third, it lacks flexibility to incorporate external factors which are known to help mobility prediction (i.e., contextual information).In this dissertation, we revisit this state-of-the-art predictability technique, aiming at tackling these limitations as well as at providing techniques to use predictability information in practical applications.