A Mobility Model for Synthetic Travel Demand From Sparse Traces

Knowing how much people travel is essential for transport planning. Empirical mobility traces collected from call detail records (CDRs), location-based social networks (LBSNs), and media data have been used widely to study patterns. However, these suffer sparsity, an issue that has largely overlooked. In order extend the use of low-cost accessible data, this proposes a model fills gaps in sparse which one can later synthesise demand. The proposed extends fundamental mechanisms exploration preferential return trips. tested on Twitter. We validate our find good agreement origin-destination matrices trip distance distributions Sweden, Netherlands, São Paulo, Brazil, compared with benchmark using heuristic method, especially most frequent range (1–40 km). Moreover, learned parameters are found be transferable region another. Using model, reasonable demand values synthesised dataset covering large enough population very individual geolocations (around 1.5 per day 100 days average).