Harnessing links between historical business and household microdata and street-view images to assess transit-induced neighborhood changes at small spatial scales

North Carolina State University, Raleigh NC

Investigators

Abstract

This project investigates transit-induced commercial and residential gentrification and displacement through a first-of-its-kind merge of historical market research microdata of individual businesses and households with highly localized data from street-view images, online reviews, and real estate websites. With advanced Artificial Intelligence techniques, this research seeks to unveil the complex processes of neighborhood change and migration patterns around transit stations and, meanwhile, develops versatile tools for analyzing neighborhood dynamics in diverse urban contexts. The research findings can inform policies to mitigate adverse effects on vulnerable businesses and residents and support equitable urban development. Distinguished from previous research with limited samples, this project integrates data from multiple sources to cover the full populations of households, businesses, and housing in a region. Expanding upon causal economic analysis and urban gentrification theories, the project develops innovative data fusion techniques, machine learning models, spatial analysis, and quasi-experimental econometric models to effectively capture the impacts of transit investments on different types of businesses and households. Research objectives include identifying vulnerable businesses, the typologies of establishments that tend to replace them, and the socioeconomic profiles of households and their likelihood of migrating into or exiting station areas. The project examines the accuracy and reliability of socioeconomic microdata and develops a methodological framework for neighborhood dynamics analysis adaptable broadly for research with microdata to understand urban processes and dynamics. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.