Here we leverage large-scale travel surveys covering over 200,000 residents across Boston, Chicago, Hong Kong, London and São Paulo. With rich individual-level data, we reveal patterns in social mixing, which cannot be identified from high-resolution mobility data alone. Inferring socioeconomic status from residential neighborhoods yields social mixing levels 16% lower than using survey data. Individuals over the age of 66 experience greater social mixing than those in late working life (aged 55–65), lending data-driven support to the ‘second youth’ hypothesis. Teenagers and women with caregiving responsibilities exhibit lower social mixing levels. Living near major transit stations reduces the influence of socioeconomic status on social mixing. Finally, inputs of home-space, activity-space and demographic attributes are embedded and fed into a supervised autoencoder, revealing that mobility shapes experienced social mixing more than sociodemographic characteristics, home environment and transit proximity. Yet, activity spaces remain stratified by income, resulting in structurally different social mixing experiences.
NetSI authors
