A city is not a static tree: understanding urban areas through the lens of real-time behavioral data

Abstract

Cities are the main ground on which our society and culture develop today and will develop in the future. Against the traditional understanding of cities as physical spaces mostly around our neighborhoods, recent use of large-scale mobility datasets has enabled the study of our behavior at unprecedented spatial and temporal scales, much beyond our static residential spaces. Here we show how it is possible to use these datasets to investigate the role that human behavior plays in traditional urban problems like segregation, public health, or epidemics. Apart from measuring or monitoring such problems in a more comprehensive way, the analysis of those large datasets using modern machine learning techniques or causality detection permits to unveil of the behavioral roots behind them. As a result, only by incorporating real-time behavioral data can we design more efficient policies or interventions to improve such critical societal issues in our urban areas.