Prioritizing the poorest and most vulnerable in West Africa: Togo's Novissi platform for social protection uses machine learning, geospatial analytics, and mobile phone metadata for the pandemic response

Summary

World Bank results brief describing the Novissi programme's use of ML and geospatial data for targeting. Reports that Phase 1 covered 572,852 informal sector workers; Phase 2 used ML to target 57,000 beneficiaries in 100 poorest rural cantons. Notes IDA financing under WURI Program ($72 million for SP delivery systems), creation of 170,278 new mobile money accounts, partnerships with UC Berkeley, IPA, Northwestern, and GiveDirectly, and planned surveys to detect bias against women, illiterate, and marginalised groups.