Automatic Classification of Points-of-Interest for Land-use Analysis


Filipe Rodrigues (fmpr [at]
Ana O. Alves
Shan Jiang
Joseph Ferreira
Francisco Câmara Pereira


This article describes a methodology for automatic classification of places according to the North American Industry Classification System (NAICS). This taxonomy is applied in many areas, particularly in Urban Planning. The typical approach is to manually classify places/Points of Interest that are collected with field surveys. Given the financial costs of the task some semi-automatic approaches have been taken before, but they are still based on field surveys and official census. In this article, we apply machine learning to fully automatize NAICS classification of POIs collected from online sources. We compare the adequacy of several algorithms to the task, using both flat and hierarchical approaches. We validate the results in the Urban Planning context.


Machine learning, Spatial analysis, Points-of-interest, Urban planning, GIS


GEOProcessing, 2013