The Best Place in Tokyo for Anything: Classifying Stations by Walkability to Specific Amenities

Walkability analyses have recently gained attention for economic, health, and environmental reasons [5, 8, 13]. We examine the walkable store profiles for train stations of central Tokyo and use machine learning to find clusters of similarly walkable areas. First, we use a breadth-first search algorithm on the road network to determine the walkable areas within 5, 10, and 15 min of each station. We then collect the establishments within 50 m of any traversed edge. We perform three analyses: (1) classifying regions by the numbers of stores of each type, (2) recursive feature selection and reclassification, and (3) scoring areas by their specialization in one of the store categories. We find that classification without feature selection produces more useful results, and that the <15 min isochrones yield the best results. These methods can be broadened to identify regions that are over- and under-serviced by amenities with impacts for both policy and business planning.