An inherent limiting factor of human mobility prediction

Licia Amichi (1, 2) , Aline Carneiro Viana (2) , Mark Crovella (3) , Antonio Loureiro (4)

1 IP Paris - Institut Polytechnique de Paris
2 TRiBE - inTeRnet BEyond the usual
3 Boston University - Computer Science Department [Boston]
4 UFMG - Universidade Federal de Minas Gerais = Federal University of Minas Gerais [Belo Horizonte, Brazil]

Predicting how we humans move within space and time is becoming a central topic in many scientific domains, ranging from epidemic propagation, urban planning to ride-sharing. However, current works neglect individuals' preferences for exploration and discovery of new places. Yet, noveltyseeking activities appear to have significant consequences on the ability to understand and predict individuals' trajectories. In this work, we propose a new approach for the identification of moments of novelty-seeking. Subsequently, we construct individuals' mobility profiles based on their exploration inclinations-Scouters (i.e., extreme explorers), Routiners (i.e., extreme returners), and Regulars (i.e., without extreme behavior).

Mots clés: Individual Mobility; Exploration; Mobility Profiling

Domaines: Informatique [cs]

Licia Amichi, Aline Carneiro Viana, Mark Crovella, Antonio Loureiro. An inherent limiting factor of human mobility prediction. [Research Report] INSTITUT POLYTECHNIQUE DE PARIS; INRIA Saclay, équipe Tribe. 2021. ⟨hal-03130267⟩