DRAFT: Using mobile call detail records (CDRs) and remote sensing data for spatial mapping of poverty


Posted on September 6, 2023  /  0 Comments

Ending all forms of poverty remains a primary global challenge and a key objective of the Sustainable Development Goals (SDGs). To effectively combat poverty, access to accurate information about the locations of affected populations is vital. This data enhances our comprehension of poverty’s root causes, facilitates optimized resource allocation for poverty alleviation initiatives, and is a fundamental element in monitoring poverty rates over time. While censuses and surveys are the established benchmarks for measurement and the foundation of targeted social assistance programs like cash transfers, they are often resource-intensive and time-consuming. This makes them impractical for rapid deployment during emergencies and continuous monitoring of spatial and temporal poverty disparities, which is essential for comprehensive development strategies. To bridge this gap, this study examines the potential of utilizing publicly available data sources, both from the public and private sectors, to gain fresh insights into poverty’s spatial distribution. By employing unsupervised and supervised machine learning techniques, we explore the feasibility of utilizing mobile call detail records (CDRs) as well as geographic information system (GIS) and remote sensing (RS) data to map poverty spatially. Despite the limitation of lacking comprehensive, precise ground truth data for full validation, initial findings suggest the approach holds promise in achieving higher spatial and temporal resolutions for poverty mapping.

  Download PDF   Email

Comments are closed.