Proactive AI-Driven Benefit Assignment — Azerbaijan's State Social Protection Fund System
Azerbaijan
Azerbaijan's State Social Protection Fund uses AI-based data matching across 15+ agencies to proactively identify and enrol eligible citizens in …
Senegal · Dakar · See the Senegal profile
Senegal's DGPSN uses a proxy-means-test score from the Registre National Unique to target Family Security Grants, reaching 355,013 beneficiaries in Q1 2026 — the World Bank calls its coverage Africa's largest, though informal-sector exclusion persists.
Senegal's Délégation Générale à la Protection Sociale et à la Solidarité Nationale (DGPSN), established in 2012, runs the Registre National Unique (RNU), a household registry used to target the country's flagship cash-transfer programme. The RNU computes a Proxy Means Test (PMT) score from socio-economic household data collected by the national statistics agency (ANSD), and the lowest-scoring households in each locality become beneficiaries of the Programme National de Bourses de Sécurité Familiale (PNBSF). The registry was institutionalised by decree n°2021-1052 of 2 August 2021, which set a target of extending coverage to one million households.
ANSD collects the socio-economic data used to compute each household's PMT score, and DGPSN uses that score to select the poorest households in each locality for enrolment in the PNBSF cash-transfer programme. Selected beneficiaries receive quarterly cash payments disbursed through the postal operator La Poste; for the first quarter of 2026, payments began on 19 March 2026. The registry is meant to be updated on an ongoing basis to keep household scores accurate as circumstances change.
By 2024 the RNU covered roughly 541,192 households, working toward the decree's one-million-household target. For the first quarter of 2026, Senegal's national broadcaster RTS reported that 355,013 beneficiaries each received a payment of 35,000 CFA francs. A World Bank economist described Senegal in 2019 as having "the largest coverage rate in Africa" for this type of registry, while April 2026 reporting from Guinée-Éco noted that coverage remains limited for informal-sector workers and that financial resources remain insufficient.
The source material characterises the RNU/PNBSF as a statistical proxy-means-test scoring formula rather than a trained machine-learning model, placing it in the same "algorithmic social-benefit targeting" category as comparable systems already catalogued in Chile, Pakistan, Jordan and Togo. Broader World Bank research on PMT-based targeting is noted to generally document real inclusion and exclusion error risks for this class of method, consistent with the informal-sector coverage gaps flagged in more recent reporting on Senegal's own registry.
Where this practice's information was retrieved from, and when.
Azerbaijan
Azerbaijan's State Social Protection Fund uses AI-based data matching across 15+ agencies to proactively identify and enrol eligible citizens in …
Togo
To rush COVID aid to the poorest, Togo used machine learning on satellite imagery and mobile-phone data to target cash …
Kazakhstan
Kazakhstan's Digital Family Card uses predictive scoring across 100+ socio-economic indicators from 20+ agencies to proactively identify and serve vulnerable …
Mongolia
E-Mongolia (2020) consolidates 1,263 public services from 87 agencies. By 2025: 1.8 M active users (88% of adults), 46 M …
Open full copilot Grounded in cited practices — always check the sources.