Registro Social de Hogares — Chile's algorithmic social-benefit targeting system
Chile
Chile's RSH algorithm classifies 8.99 million households (85.6 % of the population) into socioeconomic tiers that gate access to all …
Pakistan · Islamabad · See the Pakistan profile
Pakistan's BISP operates a 35-million-household registry using Proxy Means Test scoring cross-referenced with NADRA biometric data to identify the poor; 15 million families receive transfers and 820,000 ineligibles were removed after the 2019–2021 national data update.
Pakistan's Benazir Income Support Programme (BISP) operates the National Socio-Economic Registry (NSER), a large-scale household database built through door-to-door surveys covering over 35 million households, more than 85% of Pakistan's total.
To generate a welfare score for each household via a Proxy Means Test algorithm using dwelling quality, asset ownership, demographic composition, and adult employment and education levels, to target Kafalat quarterly cash transfers to households below an eligibility threshold.
A major data collection cycle ran 2019-2021, correcting coverage gaps from the original 2011 survey. Records are cross-referenced with the NADRA biometric identity system via a Cognitive API integration to match household members to biometric IDs and expose registration inconsistencies. Since 2022, Dynamic Registration Centres in every tehsil allow continuous self-registration and updates.
Cross-matching with NADRA revealed inclusion errors: approximately 820,000 women who failed updated eligibility checks were removed from the programme. Outreach simultaneously expanded coverage to 15 million families, tripling beneficiary households from pre-reform levels, while the total digital survey covered 34 million households in 24 months. The Asian Development Bank committed $603 million in 2020 to support Ehsaas (merged with BISP in 2022). World Bank assessments have identified remaining exclusion errors among extremely poor households not reached by the initial survey.
The Lancet cited the programme as a model for advancing universal social protection in a fragmented system; its distinctive contribution is scale — the largest biometrically cross-referenced social registry in South Asia — and a dynamic, self-updating architecture beyond one-time surveys.
Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.
Where this practice's information was retrieved from, and when.
Chile
Chile's RSH algorithm classifies 8.99 million households (85.6 % of the population) into socioeconomic tiers that gate access to all …
Togo
To rush COVID aid to the poorest, Togo used machine learning on satellite imagery and mobile-phone data to target cash …
Jordan
Jordan's National Aid Fund uses a 57-factor algorithm to target 250,000+ households under Takaful, World Bank co-designed. HRW (2023) and …
Switzerland
SPSP integrates AI-powered genomic analysis to detect pathogen variants across Switzerland. Mandated by the Federal Office of Public Health since …
Open full copilot Grounded in cited practices — always check the sources.