Synthesising digital twin travellers: Individual travel demand from aggregated mobile phone data

Mobile phone data generated in mobile communication networks has the potential to improve current travel demand models and general, how we plan for better urban transportation systems. However, due its high-dimensionality, even if anonymised there still exists possibility re-identify users behind traces. This risk makes usage outside telecommunication network incompatible with recent privacy regulations, hampering adoption transportation-related applications. To address this issue, propose a framework designed only user-aggregated synthesise realistic daily individual mobility — Digital Twin Travellers. We explore different strategies built around modified Markov an adaption of Rejection Sampling algorithm recreate schedules locations. also define one-day population score measure similarity between agents real user population. Ultimately, show series histograms provided by service provider (TSP) it is possible plausible disaggregate them into new synthetic useful individual-level information, building way big that accordance regulations.