Indexical Cities: Articulating Personal Models of Urban Preference with Geotagged Data

TL;DR

This paper introduces a machine learning approach that uses geotagged images to model individual urban preferences, enabling personalized predictions of likable places without relying on traditional city rankings.

Contribution

It presents a novel method for capturing personal urban preferences through geotagged data and machine learning, moving beyond objective city quality metrics.

Findings

Successfully predicts personal preferences for urban locations.

Demonstrates applicability across diverse urban cultures.

Provides a framework for personalized urban experience modeling.

Abstract

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.