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

Abstract

This paper describes a methodology for automatic classification of places according to the North American Indus- try Classification System. 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 paper, we apply machine learning to fully automatize the classification of Points-of-Interest collected from online sources. We compare the adequacy of several algorithms to the task, using both flat and hierarchical approaches, and validate the results in the Urban Planning context. Keywords-machine learning; space analysis; points-of-interest; urban planning; GIS.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 21 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.