What Google Street View reveals about neighbourhood incomes

An algorithm built by Stanford University researchers combed through 50 million Google Street View images from 200 US cities, recognizing the year, model and make of every car in every image. By comparing those findings with data from the American Community Survey, which collects information ranging from gender and education to unemployment and voting preferences, the researchers could accurately predict a host of demographic identifiers such as income, race and even political views from the types of cars found in each community.

This new approach has implications for how large-scale income data can be collected in the future.