Estimating Economic Characteristics with Phone Data
This research aims to develop new methods for generating cost-effective maps of poverty and vulnerability in Afghanistan
Abstract
The goal of this research is to develop new methods for generating cost-effective maps of poverty and vulnerability in Afghanistan, based on the analysis of large-scale “digital exhaust” from communications networks. Specifically, we intend to develop techniques that generate high-resolution maps and measurements of population characteristics based on regionally-aggregated patterns of mobile phone use. Our team has previously demonstrated the feasibility of this approach using a combination of phone surveys and mobile phone metadata from Rwanda. Over the past two years, we have developed a strong partnership with the largest mobile phone operator in Afghanistan, who has given us access to several terabytes of mobile phone records, and permission to conduct follow-up phone surveys with their customer base. We thus have a unique opportunity to transform our pilot study into a set of metrics and maps that can provide new insight into the demographic and economic structure of the Afghan population.
This work is part of the International Growth Centre’s ‘High-Resolution Measures of Poverty and Vulnerability in Afghanistan: Cost-Effective Solutions Based on Mobile Phone Data’ project
Citation
Blumenstock, Joshua E. 2018. Estimating Economic Characteristics with Phone Data. AEA Papers and Proceedings, 108 : 72-76.DOI: 10.1257/pandp.20181033