Relative Weatlh Index Data

It has been built by researchers at the University of Carlifornia - Berkeley and Facebook. The estimates are built by applying machine learning algorithms to vast and heterogeneous data from satellites, mobile phone networks, topographic maps, as well as aggregated and de-identified connectivity data from Facebook.

They train and calibrate the estimates using nationally-representative household survey 20 data from 56 LMICs, then validate their accuracy using four independent sources of household survey data from 18 countries. They also provide confidence intervals for each micro-estimate to facilitate responsible downstream use. The data is provided for 93 low and middle-income countries at 2.4km resolution.