Using publicly available data for predicting socioeconomic values in urban context

Abstract Urban transportation networks are recognized for their pivotal role in forecasting city indicators and facilitating efficient planning and management. However, despite the increase of methodologies and models harnessing machine learning advancement to forecast these values, challenges persist in scenarios where direct demographic or economic data are limited or unavailable. In this paper, we propose an approach to infer socioeconomic information in an urban context without relying on traditional, official data sources, but rather focusing on publicly available data relating to the digital footprints of the cities’ inhabitants. We leverage Graph Neural Network (GNN) models to capture the spatial relationships inherent in network data while integrating perceptual features extracted from images to enhance predictive accuracy. Our results demonstrate that the combination of these data sources enables a GNN to achieve robust performance in predicting socioeconomic indicators, particularly in settings where traditional demographic and economic data may be sparse or unavailable. Through our analysis, we show that while perceptual features alone offer substantial predictive power, the inclusion of map topology through GNN models provides crucial context, leading to better generalization and more reliable predictions across different urban areas.