Indexical Cities: Articulating Personal Models of Urban Preference with Geotagged Data
This addresses the need for personalized urban assessment, offering a novel alternative to global city rankings, though it is incremental in applying existing ML techniques to a new domain.
The research tackled the problem of predicting personal urban preferences for unknown cities or neighborhoods using geotagged images and machine learning, resulting in a method that characterizes individual views and forecasts likeable places for specific observers.
How to assess the potential of liking a city or a neighborhood before ever having been there. The concept of urban quality has until now pertained to global city ranking, where cities are evaluated under a grid of given parameters, or either to empirical and sociological approaches, often constrained by the amount of available information. Using state of the art machine learning techniques and thousands of geotagged satellite and perspective images from diverse urban cultures, this research characterizes personal preference in urban spaces and predicts a spectrum of unknown likeable places for a specific observer. Unlike most urban perception studies, our intention is not by any means to provide an objective measure of urban quality, but rather to portray personal views of the city or Cities of Indexes.