Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Predicting neighborhoods' socioeconomic attributes using restaurant data.

Lei Dong1,2, Carlo Ratti1, Siqi Zheng3

  • 1Senseable City Lab, Department of Urban Studies and Planning, Massachusetts Institute of Technology, Cambridge, MA 02139.

Proceedings of the National Academy of Sciences of the United States of America
|July 17, 2019
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Self-reconfiguring modular robotic boats.

Nature communications·2026
Same author

Octopus: A low-cost, modular environmental sensing platform for makers.

HardwareX·2026
Same author

Investigating the role of urban shade on ground-level ozone pollution in cities.

Environmental research·2026
Same author

Evaluation of LiDAR devices and data to conduct terrestrial surveys in favelas.

Scientific data·2026
Same author

Unsupervised mapping of urban tree diversity using spatially-aware visual clustering.

Scientific reports·2026
Same author

Smartwatch detection of atrial flutter and atrial fibrillation: when the apple falls far from the tree - case report.

Future cardiology·2026

Restaurant data can accurately predict neighborhood socioeconomic attributes like population and employment, bridging data gaps in developing cities. This method offers timely, high-resolution insights for urban planning and policy.

Area of Science:

  • Urban Studies
  • Data Science
  • Socioeconomics

Background:

  • High-resolution socioeconomic data is crucial for urban planning but often scarce in developing regions.
  • Neighborhood-level data on population, employment, and enterprise activity is vital for effective policy implementation.

Purpose of the Study:

  • To demonstrate how readily available restaurant data can predict socioeconomic attributes of urban neighborhoods.
  • To develop and validate machine-learning models for estimating key socioeconomic indicators using location-based data.

Main Methods:

  • Merged online restaurant data with microdatasets across nine Chinese cities.
  • Extracted features from restaurant data to train machine-learning models.
  • Estimated daytime/nighttime population, firm counts, and consumption levels at various spatial resolutions.
Keywords:
machine learningrestaurantsocial goodsocioeconomic dataurban studies

Related Experiment Videos

Main Results:

  • Machine-learning models achieved 90-95% accuracy in predicting socioeconomic variations across neighborhoods.
  • Analyzed trade-offs between accuracy, spatial resolution, and sample size.
  • Demonstrated model transferability across different cities, highlighting cross-city generality.

Conclusions:

  • Easily accessible restaurant data serves as a reliable proxy for neighborhood socioeconomic status.
  • This approach effectively bridges urban data gaps, enabling data-driven policy in data-scarce environments.
  • The method's cross-city transferability facilitates broader application of big data analytics in urban planning.