Program Targeting with Machine Learning and Mobile Phone Data: Evidence from an Anti-Poverty Intervention in Afghanistan
This addresses targeting inefficiencies in humanitarian aid for vulnerable populations, though it is incremental in applying existing ML methods to new data.
The study tackled the problem of accurately identifying ultra-poor households for anti-poverty programs in Afghanistan by using machine learning with mobile phone data, showing that it performs nearly as well as survey-based methods and combining both sources improves accuracy.
Can mobile phone data improve program targeting? By combining rich survey data from a "big push" anti-poverty program in Afghanistan with detailed mobile phone logs from program beneficiaries, we study the extent to which machine learning methods can accurately differentiate ultra-poor households eligible for program benefits from ineligible households. We show that machine learning methods leveraging mobile phone data can identify ultra-poor households nearly as accurately as survey-based measures of consumption and wealth; and that combining survey-based measures with mobile phone data produces classifications more accurate than those based on a single data source.