Researchers at Imperial College London in the U.K. have trained an artificial intelligence (AI) system to detect inequalities in four U.K. cities—London, Birmingham, Manchester, and Leeds—using a combination of government statistics and public images taken from Google Street View.
The AI was trained on 525,860 images from 156,581 postal codes across London, along with income, health, crime, housing, and living environment statistics about the areas.
The researchers withheld 20% of the data to test how closely the algorithm's estimation matched actual distributions of inequality.
The AI was most successful at spotting differences in quality of the living environment and average income, scoring 0.86 for both on a statistical test of how closely its predictions matched with the real data.
The system was least successful at predicting differences in crime rate and self-reported health, scoring 0.57 and 0.66, respectively.
From New Scientist
View Full Article
Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA