Inclusive mobility: trajectory patterns of older adults

Urban mobility faces a silent challenge: the data that feeds planning systems is often biased toward majority groups, leaving out groups such as older adults. This imbalance not only distorts predictive models but also perpetuates cities designed for a typical user that does not represent the entire population. Recent research on trajectory patterns shows that older adults exhibit distinctive spatial behaviors —smaller activity radius, asymmetric schedules, and reduced entropy— that need to be accurately captured to avoid exclusionary infrastructure. From a technical perspective, the solution involves integrating artificial intelligence and AI agents capable of learning from balanced datasets, but the first challenge is having platforms that allow collecting, processing, and analyzing this data ethically and scalably. At Q2BSTUDIO we develop custom applications that facilitate the integration of multiple mobility sources —from IoT sensors to shared bike records— ensuring the representation of all age groups. Furthermore, our experience in AI for businesses allows us to design models that actively correct demographic biases, improving prediction fidelity for underrepresented groups. To sustain these processes, we offer AWS and Azure cloud services that ensure distributed storage and processing of large volumes of geospatial data, as well as cybersecurity to protect citizens' privacy. Finally, business intelligence tools such as Power BI allow urban planners and managers to visualize hidden patterns and make informed decisions. Building inclusive cities is not only a social issue but also a technical challenge that requires custom software and a commitment to the faithful representation of human diversity.