Short-term prediction and visualization of parking area states in real-time : a machine learning approach

Public road authorities and mobility service providers need information about future traffic states to act pro-actively upon the dynamics of the urban road network. In this research, a machine learning methodology for predicting influx, outflux and occupancy rate of parking areas on a horizon of up to 60 minutes has been developed. Based on a thorough process applied to a real-world case in the city of Arnhem, the feed-forward neural network turns out to outperform the random forest on all assessed performance measures, even though the differences are small and both are outperforming a naive (seasonal random walk) model. Overall, the selected configuration shows a performance gain of 235% in comparison with the naive model. Furthermore, it is shown that predicting the in- and outflux is a far more difficult task than predicting occupancy rate. Results also suggest that relatively little training data is needed to maintain satisfactory predictive performance. This is a promising finding regarding potential expansion of the system towards other parking areas, especially in cases where data availability is substandard. During real-time deployment, the model shows to perform 172% better than the naive model. As a result, it can provide valuable information for pro-active traffic management.