Google Street View image predicts car accident risk

Kita-Wojciechowska Kinga () and Kidziński Łukasz
Additional contact information
Kita-Wojciechowska Kinga: Faculty of Economic Sciences, University of Warsaw, Poland
Kidziński Łukasz: Department of Bioengineering, Stanford University, Stanford, CA, USA

Central European Economic Journal, 2019, vol. 6, issue 53, 151-163

Abstract: Road traffic injuries are a leading cause of death worldwide. Proper estimation of car accident risk is critical for the appropriate allocation of resources in healthcare, insurance, civil engineering and other industries. We show how images of houses are predictive of car accidents. We analyse 20,000 addresses of insurance company clients, collect a corresponding house image using Google Street View and annotate house features such as age, type and condition. We find that this information substantially improves car accident risk prediction compared to the state-of-the-art risk model of the insurance company and could be used for price discrimination. From this perspective, the public availability of house images raises legal and social concerns, as they can be a proxy of ethnicity, religion and other sensitive data.

Keywords: Generalized Linear Model; risk modelling; insurance pricing; satellite imagery; Google Street View (search for similar items in EconPapers)
JEL-codes: C52 C83 G22 (search for similar items in EconPapers)
Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.2478/ceej-2019-0011 (text/html)

Related works:
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:vrs:ceuecj:v:6:y:2019:i:53:p:151-163:n:9

DOI: 10.2478/ceej-2019-0011

Access Statistics for this article

Central European Economic Journal is currently edited by Anna Matysiak

More articles in Central European Economic Journal from Sciendo
Bibliographic data for series maintained by Peter Golla ().