Dynamic monitoring of taxi demand profiles, utilizing location-specific information in large metropolitan areas

Urban mobility, especially in Metropolitan Areas has drawn the attention of scientists for many decades. As increasing volumes of urban data are captured and become available, new opportunities arise for data-driven analysis that can lead to improvements in the lives of citizens through evidence-based decision support systems and policies. Sensing and wireless networking technologies are increasingly deployed in transportation systems due to the fact that they provide updated and reliable information. In this study, Taxi demand profiles are monitored from data that offer the real-time occupancy status and Global Positioning System (GPS) location for three taxi fleets, during the New Year's day. This dataset provides rich spatiotemporal information about customers demand and their mobility patterns. However, analyzing these data presents many challenges. The data are complex, containing geographical and temporal components in addition to multiple variables associated with each trip. Despite all these, real-time information gives us the opportunity to export variety of `heatmaps', providing evidence relating to the mobility of the day. Furthermore, the conclusions of this study should help improve coordination of taxi services quality and increasing taxi fleet utilization.