Predicting Traffic Congestion in Presence of Planned Special Events

The recent availability of datasets on transportation networks with high spatial and temporal resolution is enabling new research activities in the fields of Territorial Intelligence and Smart Cities. Within these domains, in this paper we focus on the problem of predicting traffic congestion in urban environments caused by attendees leaving a Planned Special Events (PSE), such as a soccer game or a concert. The proposed approach consists of two steps. In the first one, we use the K-Nearest Neighbor algorithm to predict congestions within the vicinity of the venue (e.g. a Stadion) based on the knowledge from past observed events. In the second step, we identify the road segments that are likely to show congestion due to PSEs and map our prediction to these road segments. To visualize the traffic trends and congestion behavior we learned and to allow Domain Experts to evaluate the situation we also provide a Google Earthbased GUI. The proposed solution has been experimentally proven to outperform current state of the art solutions by about 35% and thus it can successfully serve to reliably predict congestions due to PSEs.