Program targeting with machine learning and mobile phone data: Evidence from an anti-poverty intervention in Afghanistan

• 成果类型: Article
• 署名作者: Aiken, Emily L.; Bedoya, Guadalupe; Blumenstock, Joshua E.; Coville, Aidan
• 署名单位: University of California System; University of California Berkeley; The World Bank
• 刊物名称: JOURNAL OF DEVELOPMENT ECONOMICS
• ISSN/ISSBN: 0304-3878
• DOI: 10.1016/j.jdeveco.2022.103016
• 发表日期: 2023
• 关键词: targeting; Machine Learning; Mobile phone data; Afghanistan

摘要

Can mobile phone data improve program targeting? By combining rich survey data from a big pushantipoverty 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.