Modelling human mobility is crucial in several scientific areas, from urban planning to epidemic modeling, traffic forecasting, and what-if analysis. Existing models focus on the spatial and temporal dimensions of mobility only, while the social dimension is often neglected. We propose STS-EPR, a mechanistic generative model that captures the spatial, temporal, and social dimensions of human mobility together. Our results show that STS-EPR generates realistic trajectories, making it better than models that lack either the social, spatial, or temporal mechanisms. STS-EPR is a step towards the design of mechanistic models that can capture all the aspects of human mobility in a comprehensive way.

The model is available in the scikit-mobility Python library (https://github.com/scikit-mobility/scikit-mobility/blob/master/skmob/models/sts_epr.py)