Taxi Stand Layout Planning Using Trip Spatial Density Clustering Algorithm

Arbitrary stopping of taxis has a negative impact on urban traffic. This paper conducts the layout planning of taxi stands based on GPS trajectory data and takes the spatial distribution of taxi trip origins as reference. Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) algorithm is applied to cluster the spatial density of taxi trip origins, and the center points of the clusters are used for the layout of taxi stands. Using central Chongqing, an area with rich land use and high population, the spatial distribution of taxi trip origins is extracted to study taxi stand layout planning. Results show 107 potential locations are distributed in commercial and residential areas, consistent with the spatial distribution of high-demand areas. Taxi stands should also be placed considering the characteristics of the surrounding areas. The methodology of this paper can provide technical means for transportation facility planning and traffic management.