Google Maps POIs used to estimate income in Sao Paulo

Researchers have developed a method to estimate household income at a sub-municipal level in São Paulo, Brazil, by analyzing crowd-sourced data from Google Maps Points of Interest (POIs). This approach uses POI categories from Google Places to create high-frequency, low-cost income proxies, addressing the limitations of Brazil's infrequent and costly decennial census. The best-performing model, combining Non-negative Matrix Factorization with gradient boosting, achieved an R^2 of 0.65 in predicting census-derived income, suggesting that geospatial data can effectively supplement traditional income statistics. AI

IMPACT Demonstrates novel applications of geospatial and machine learning techniques for socio-economic data analysis.

RANK_REASON Academic paper detailing a new methodology for income estimation. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Brazil
• Google Maps
• Google Places
• gradient boosting
• non-negative matrix factorization
• principal component analysis
• São Paulo

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →