Scalable Targeting of Social Protection: When Do Algorithms Out-Perform Surveys and Community Knowledge?

Emily Aiken, Anik Ashraf, Joshua E. Blumenstock, Raymond P. Guiteras and A. Mushfiq Mobarak

CEnREP Working Paper 25-001, November 2025, https://go.ncsu.edu/cenrep-wp-25-001. Under review.

Latest Draft (PDF), Nov. 2025.

Abstract: Advances in digital data and algorithms are enabling new approaches to poverty targeting at scale. Using rich data from Bangladesh and Togo, we compare an algorithmic approach based on machine learning and mobile phone data to status quo targeting with proxy means tests and community-based targeting. While proxy means tests are most accurate, algorithmic targeting is more cost effective for programs where the budget is small relative to the number of households screened. Combining our estimates with global program data, we estimate that phone-based targeting would be the welfare-maximizing approach for up to 30% of countries' social assistance programs.

Previous version (June 2025):

NBER Working Paper 33919, doi:10.3386/w33919.

CEPR Discussion Paper No. 20332, https://cepr.org/publications/dp20332. (Gated.)

CESifo Working Paper No. 11928, https://www.ifo.de/en/publications/2025/working-paper/scalable-targeting-social-protection-when-do-algorithms-out-perform. PDF (open).

Media:

"Living in remote areas shouldn’t be a death sentence," Financial Times, 20 August 2025.