Stanford scientists have used an artificial intelligence system and publicly available data from Google Street View to predict income levels and voting patterns of neighbourhoods in the US. The system analysed 50 million images from the street- scene feature of Google’s mapping service. Helped by recent advances in artificial intelligence, researchers from Stanford University in the US collected details about cars in the millions of images, including makes and models. By linking the information with other data sources, the project was able to predict factors like pollution and voting patterns at the neighbourhood level.
“This kind of social analysis using image data is a new tool to draw insights,” Timnit Gebru, who led the research, was quoted as saying by ‘Tech Crunch’. The car-image project involved 50 million images of street scenes gathered from Google Street View. In them, 22 million cars were identified, and then classified into more than 2,600 categories like their make and model, located in more than 3,000 ZIP codes and 39,000 voting districts.
