Using AI and Digital Data to Target Cash Transfers in Togo

Summary

CEGA project case study describing the Novissi targeting workflow. It reports that the team used satellite-based models to support targeting to the 100 poorest cantons, then matched survey responses to call detail record data to train phone-based poverty prediction models. The case study reports a 42% improvement in targeting precision relative to naive geographic targeting and states that 154,238 citizens received unconditional cash transfers between December 2020 and April 2021 through the scaled approach.