Oct 9th, 2018 - Modeling and Planning Urban Systems with Novel Data Sources
Urban mobility models are important in a wide range of application areas. Current mainstream models require socio-demographic information from costly manual surveys, which are in small sample sizes and updated in low frequency. In this study, we propose a novel individual mobility modeling framework, TimeGeo, that extracts all required features from ubiquitous, passive, and sparse digital traces in the information age. Combining demographic data, road network information and billions of mobile phone records, we infer travel demand profiles and estimate travel times across five different cities. We demonstrate that the percentage of time lost in congestion is a function of the proportion of vehicular travel demand to road infrastructure capacity, and is closely tied to spatial density and selfish choices of drivers. In this context we explore the feasibility of smart routing applications during mega events.