On-Street Parking Prediction: A Comparative Study

Urban computing techniques harnessing digital mobility traces can assume a pivotal role in comprehending travel patterns and behavioral dynamics within an urban context. These methodologies yield invaluable insights for transportation planners, enabling them to make informed decisions and augment the overall efficiency of urban transportation systems. The goal of this research is to analyze the parking phenomenon in urban areas and develop predictive models for parking-related indicators. Specifically, we introduce two quantitative metrics: the Average Parking Time and the Average Number of Simultaneously Parked Vehicles, aimed at characterizing parking activities from temporal and volumetric perspectives. A large collection of raw GPS traces from a sample of private cars in the metropolitan areas of Rome was used to investigate and model the spatiotemporal dynamics of parking demand and saturation on public streets. Our investigation entailed the application of a diverse array of Machine Learning and Deep Learning techniques, encompassing statistical models, Graph Convolutional Networks (GCNs), and Convolutional Neural Networks (CNNs), for the prediction of these indicator values. In our experiments, we found that the 3D-CLoST model excelled in accurately predicting parking indicators compared to other techniques. Interestingly, we also observed that statistical models were able to achieve performance levels that were similar to those of more complex models.