Identifying urban areas by combining human judgment and machine learning: An application to India

Virgilio Galdo, Yue Li and Martin Rama

Journal of Urban Economics, 2021, vol. 125, issue C

Abstract: We propose a methodology for identifying urban areas that combines subjective assessments with machine learning, and we apply it to India, a country where several studies see the official urbanization rate as an under-estimate. For a representative sample of cities, towns and villages, as administratively defined, we rely on human judgment of Google images to determine whether they are urban or rural in practice. We collect judgments across four groups of assessors, differing in their familiarity with India and with urban issues, following two different protocols. We then combine the judgment-based classification with data from the population census and from satellite imagery to predict the urban status of the sample. The Logit model, and LASSO and random forests methods, are applied. These approaches are then used to decide whether each of the out-of-sample administrative units in India is urban or rural in practice. We do not find that India is substantially more urban than officially claimed. However, there are important differences at more disaggregated levels, with “other towns” and “census towns” being more rural, and some southern states more urban, than is officially claimed. The consistency of human judgment across assessors and protocols, the easy availability of crowd-sourcing, and the stability of predictions across approaches, suggest that the proposed methodology is a promising avenue for studying urban issues.

Keywords: Urban area; Urbanization rate; Human judgment; Google images; Crowd sourcing; Population census; Satellite imagery; Machine learning (search for similar items in EconPapers)
JEL-codes: O1 O18 R1 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0094119019301068
Full text for ScienceDirect subscribers only

Related works:
Working Paper: Identifying Urban Areas by Combining Human Judgment and Machine Learning: An Application to India (2020)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:juecon:v:125:y:2021:i:c:s0094119019301068

DOI: 10.1016/j.jue.2019.103229

Access Statistics for this article

Journal of Urban Economics is currently edited by S.S. Rosenthal and W.C. Strange

More articles in Journal of Urban Economics from Elsevier
Bibliographic data for series maintained by Catherine Liu ().