evidoria

← Back to browse

Good practice Imported

SIGPTS — Chad Extends AI Biometric Deduplication to National Refugee IDs

Chad · N'Djamena · See the Chad profile · See the N'Djamena profile

Evidence: Descriptive / self-reported Top 74% 47/100 · Ask Evidence Copilot about this practice

Chad's national biometric ID platform, whose Idemia-built engine de-duplicates against a 15-million-record database in seconds, began enrolling refugees in N'Djamena and Abéché in Feb. 2025. By May, 4,000+ had NNIRs against a 7,000 pilot target and 25,000 long-term goal.

~15,000,000
Existing records screened per enrolment
~10 seconds
Deduplication screening time
>4,000
Refugees enrolled with NNIR (as of 1 May 2025)
7,000
Pilot-phase enrolment target
25,000
Longer-term enrolment goal

Details

Maturity
Scaling
Promoter
Agence Nationale des Titres Sécurisés (ANATS)
Period
2020-2026
Keywords
digital identity, public administration, refugee services

Context

Chad's Agence Nationale des Titres Sécurisés (ANATS) has run the national biometric population registry SIGPTS since 2020, screening new enrolments against roughly 15 million existing records in about ten seconds using an Idemia automated biometric identification system, but had not previously covered refugees.

Activities

In February 2025, with World Bank funding and support from UNHCR and Chad's refugee agency CNARR, ANATS began enrolling refugees — most fleeing conflict in Sudan, the Central African Republic and Nigeria — issuing biometrically verified National Refugee Identification Numbers (NNIRs) in N'Djamena and Abéché. In March 2026, ANATS agreed to connect the registry to other government systems, starting with the Ministry of Finance, under the 'Chad Connexion 2030' digital strategy.

Results

By 1 May 2025, more than 4,000 refugees had received an NNIR against a stated pilot-phase target of 7,000 and a longer-term goal of 25,000.

Conclusions

No published third-party audit covers deduplication accuracy, refugee data-protection safeguards, or claimed gains in access to healthcare, banking and phone registration; the pilot also reaches only a small share of the roughly 1.5 million refugees and asylum seekers UNHCR reports Chad hosts.

Implementation
Indicative cost
High (€500k–€5M)
Time to results
Long (> 3 years)
Staffing & skills
ANATS (Agence Nationale des Titres Sécurisés), UNHCR and CNARR (Chad's refugee agency), Idemia (biometric system vendor)

Conditions for success

  • Existing national biometric registry (since 2020) with proven deduplication capability extended to a new population group rather than built from scratch
  • World Bank funding paired with UNHCR/CNARR operational support for refugee enrolment sites

Common failure modes

  • No published third-party audit of deduplication accuracy or refugee data-protection safeguards
  • Pilot reaches only a small share (targeting 25,000 of ~1.5 million) of Chad's refugee population

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Similar practices you may find useful