Traditional route generation algorithms may result in many routes that few drivers choose in reality, whereas other route generation algorithms need to determine thresholds for route set generation but lack data support. To avoid invalid route generation, reduce computation time, and provide a scientific basis for the generation of navigation routes and traffic assignment, this paper confines the route set size by mining the spatial distribution range of route sets and the threshold of factors affecting route set generation. Global positioning system data are used to determine hotspots based on a hotspot origin–destination identification method. The route set spatial distribution range is mined by the standard deviational ellipse. Finally, the factors affecting the generation of route sets are selected, and the classification and regression trees algorithm is used to mine their thresholds. The results show that the spatial distribution range of route sets is elliptical, and the threshold values of the number of turns per kilometer for medium and long travel distances are 1.794 and 2.508, respectively. The maximum travel time per kilometer for long travel distance is 4.773 min. The maximum numbers of road intersections for short, medium, and long travel distance per kilometer are 1.648, 0.984, and 0.592, respectively. The implications of results on reducing the search range and time of the route set and their applications to traffic network design and route navigation are also discussed.
Exploring Intracity Taxi Mobility during the Holidays for Location-Based Marketing
