Mobility plays a crucial role in all aspects of our daily lives, including getting to and from work, running errands, and taking vacations. It is expected that individuals within the same demographics will share similar mobility behaviours. For example, commuters will generally travel to work during rush hour, parents will need to drop their kids at school, and university students will tend to go-out on Friday night.
Recent studies have identified a gender gap in human mobility, with men and women displaying different mobility behaviours. Women walk shorter distances, stay more time at home and engage more in multi-purpose trips than men. But the factors driving these differences are still unclear.
The lack of high-resolution data capturing mobility behaviour and individual socio-demographic attributes prevented researchers to test their hypothesis at scale. However, the data obtained by GPS sensors in smartphones provides the unprecedented chance to gain a rich and comprehensive under-standing of the factors influencing individuals' mobility. In this work, we will study the gender differences in mobility using a novel dataset containing multi-year GPS traces of millions of individuals worldwide, their app usage and demographics.
The goal of this project is twofold: (i) We quantify the gender gap across countries, age groups, and urban and rural areas using high-resolution data. (ii) We evaluate how socio-demographic factors, such as employment status, parenthood or the perception of safety, influence the mobility of both genders.
The diverse methods brought together by the field of Complex Systems Science are ideal to carry out this analysis. We will resort to Econometrics, Machine Learning models, and Causal Inference methods to quantify the factors influencing the gender gap in mobility.
Understanding the gendered aspects of urban mobility can improve our ability to design urban spaces and transport solutions that account for different travelling needs and ensure equal access to opportunities.