In developing countries, information about the distribution of wealth or poverty may be gleaned from someone’s mobile phone records, a new study reports.
The study, published in the journal Science, was done in Rwanda. In much of Africa, as in developing countries elsewhere, accurate statistics on poverty are difficult to collect.
“This could be a useful policy instrument to estimate the geographic distribution of poverty and wealth,” said Joshua Blumenstock, a data scientist at the University of Washington and one of the study’s authors.
He and his colleagues relied on anonymized data on billions of interactions, including details about when calls were made and received and the length of the calls. The researchers also looked at when text messages were sent, and which cellphone towers the texts and calls were routed through in order to get a rough idea of geographic location.
“So it’s the who, where and when of the call, but not the what or the why,” Dr. Blumenstock said.
They combined this information with responses collected from about 850 cellphone owners to build an algorithm that predicts how wealthy or impoverished a given cellphone user is.
Using the same model, the researchers were able to answer even more specific questions, like whether a household had electricity.
The researchers are trying to do similar work in Afghanistan, where certain areas are difficult or dangerous to access and ground surveys are not possible.
“We don’t think this method is the be-all or end-all, but in the absence of good information, this is better than nothing,” Dr. Blumenstock said.
沒有留言:
張貼留言