COD-001

WFP SCOPE – Biometric Verification at Food/Cash Distributions (DRC)

Download PDF
Congo, Dem. Rep. Sub-Saharan Africa Low income Operational Deployment (Limited Rollout) Confirmed

World Food Programme (WFP) – DRC Country Office; cooperating partners (e.g., CARITAS agents trained for biometric registration).

At a Glance

What it does Classification — Identification, verification and record linkage
Who runs it World Food Programme (WFP) – DRC Country Office; cooperating partners (e.g., CARITAS agents trained for biometric registration).
Programme WFP SCOPE – Biometric Verification at Food/Cash Distributions (DRC)
Confidence Confirmed
Deployment Status Operational Deployment (Limited Rollout)
Key Risks Not assessed
Key Outcomes WFP SCOPE biometric deduplication and verification at distribution points reduce duplicate beneficiary records and impersonation risk during aid delivery operations.
Source Quality 4 sources — Other, Report (multilateral / development partner)

WFP SCOPE is the World Food Programme's beneficiary information and transfer management platform, described by WFP as an in-house developed technology that functions as a database to securely store beneficiary information and manage the transfer of benefits. In the Democratic Republic of Congo (DRC), SCOPE is deployed for biometric verification during food and cash distributions to ensure that entitlements reach the correct beneficiaries and to prevent duplication at the beneficiary level. The DRC Country Office was one of nine country offices sampled in WFP's 2021 global internal audit of SCOPE (AR/21/08), and was the subject of a dedicated internal audit of WFP operations (AR/20/12) covering the period January to December 2019.

The biometric deduplication capability within SCOPE allows operators to identify individuals who may be registered under multiple different identities, investigate potential duplicates, and deactivate confirmed duplicated identities. According to the SCOPE User Manual, 'Deduplication ensures effective programming and is critical to ensuring that WFP and partner funds reach targeted beneficiaries as intended without duplication at the beneficiary level.' Biometric information including fingerprints and face scans are used to perform biometric deduplication. The system also supports deduplication through data analytics without the use of biometrics, as biometrics may not always be appropriate or necessary in some programmes.

The biometric deduplication process consists of several stages. First, automatic deduplication occurs when new identities are registered in SCOPE with biometric data. Their biometric information is automatically checked by the MegaMatcher Automated Biometric Identification System (ABIS). The ABIS analyses the registered biometric data for new identities and compares it against all existing registered identities in SCOPE, assigning match scores to determine whether an identity is duplicate, unique, or requires manual adjudication. Identities with a match score below 96 are automatically flagged as unique. Identities with match scores between 96 and 144 are flagged for manual adjudication, as the ABIS is unable to determine with certainty whether they represent duplicates. Identities with match scores above 144 are automatically flagged as duplicates. The SCOPE User Manual notes that as MegaMatcher ABIS is further optimised, these match score ranges may change.

For identities flagged for manual adjudication, human adjudicators must manually review and determine whether the identities are genuine duplicates or distinct individuals. This human-in-the-loop process provides an important safeguard against both false positive and false negative deduplication decisions. Identities confirmed as duplicates can be downloaded as a duplicated identities list for field investigation by programme staff. Once duplicates are confirmed, the duplicated identities are deactivated so that only the individual's actual identity remains active in SCOPE.

At the global level, SCOPE had been implemented in 68 of the 85 countries where WFP has a presence by 2020, with almost 63.8 million identities registered and 20.2 million beneficiaries actively managed. A total of 3.2 million SCOPECARDs had been used globally, with PIN (32.5 percent), fingerprints (58.4 percent), or iris, QR code, or beneficiary photo (9.2 percent) as the main verification forms. SCOPE also offers a Real-Time Biometric Identification tool that allows country offices to check for duplicate records at the time of registration, which can be used both offline and online.

In the DRC specifically, the 2020 internal audit (AR/20/12) found that 2.65 million cash-based transfer beneficiaries were recorded in the DRC SCOPE platform as of February 2020, though the audit assessed that less than 50 percent of these could actually be considered active. The bulk of beneficiary data dated back to a 2016 migration exercise, where data was not properly reviewed, checked for completeness, or validated prior to its migration into SCOPE. The audit identified significant data quality issues, including 11,000 duplicate households, 1,949 duplicate electoral cards, 2,050 duplicate individuals, and 25,000 duplicated fingerprints. Eighty percent of the sampled duplicated fingerprints related either to individuals registered under different names, or to different individuals with different names and identification signs.

The DRC audit further noted that SCOPE was used only for the cash-based transfer modality, with biometric verification available only in certain locations. In locations where biometric verification was not available, the verification process was manual and performed jointly by WFP, cooperating partner, and financial service provider representatives. The Country Office did not use SCOPE for beneficiary data management of in-kind assistance, relying on Excel files instead. At the time of audit reporting, the Country Office had procured and was rolling out real-time data de-duplication software, and its data management and improvement plan had resulted in the deactivation of over one million of the 2.65 million beneficiaries in SCOPE. No privacy impact assessment had been carried out for the use of beneficiary data for either cash-based transfer or in-kind activities at the time of the 2020 audit.

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Registration primary
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Social assistance
Programme Name WFP SCOPE – Biometric Verification at Food/Cash Distributions (DRC)
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary In-Kind Transfers
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Programme Description WFP food and cash distribution programme in the Democratic Republic of Congo, using the SCOPE platform for beneficiary registration, biometric identity verification, and deduplication to ensure assistance reaches targeted beneficiaries without duplication.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Deep learning
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Monitoring, Maintenance and Decommissioning
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Not documented
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary Not documented
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary Not assessed
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Not documented
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary Not documented
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary High
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HITL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Not documented
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Not assessed
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Not assessed
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Beneficiary registries and MISPersonalSingle source (no linkage)Currently available and usedData quality issues: audit found less than 50% of 2.65 million registered beneficiaries could be considered active; 11,000 duplicate households, 1,949 duplicate electoral cards, 2,050 duplicate individuals identified. No privacy impact assessment conducted at time of audit. Data from 2016 migration not properly validated.
National ID and biometric databasesSpecial categoryLinks data across multiple systemsCurrently available and usedBiometric verification only available in certain locations in DRC; fingerprint quality can vary in field conditions; MegaMatcher ABIS match scores 96-144 require manual adjudication, adding operational burden.

United Nations Global Marketplace (2021) 'Provision of Contactless Biometrics Solutions for Iris Capture', UNGM Notice 118658. Available at: https://www.ungm.org/Public/Notice/118658 (Accessed: 30 March 2026).

View source Other

World Food Programme (n.d.). Biometric Deduplication (ABIS) – SCOPE User Manual. Rome: WFP. Available at: https://usermanual.scope.wfp.org/cash-accounts/content/intros_to_sections/deduplication.htm (Accessed 30 Oct 2025).

View source Other

World Food Programme, Office of the Inspector General (2020). Internal Audit of WFP Operations in the Democratic Republic of Congo. Internal Audit Report AR/20/12. Rome: WFP. Available at: https://docs.wfp.org/api/documents/WFP-0000118040/download/ (Accessed 23 Mar 2026).

View source Report (multilateral / development partner)

World Food Programme, Office of the Inspector General (2021). Internal Audit of SCOPE: WFP's Digital Management of Beneficiaries. Draft Internal Audit Report AR/21/08. Rome: WFP. Available at: https://docs.wfp.org/api/documents/WFP-0000128891/download/ (Accessed 23 Mar 2026).

View source Report (multilateral / development partner)
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Operational Deployment (Limited Rollout)
Year Initiated The year the AI system was first initiated or development began. 2016
Scale / Coverage The scale and geographic or population coverage of the deployment. Unknown
Funding Source The source(s) of funding for the AI system development and deployment. Unknown
Technical Partners External technology vendors, academic partners, or development partners involved. WFP SCOPE beneficiary & transfer management platform (supports registration, deduplication, authentication, and distribution tracking).
Outcomes / Results WFP SCOPE biometric deduplication and verification at distribution points reduce duplicate beneficiary records and impersonation risk during aid delivery operations.

How to Cite

DCI AI Hub (2026). 'WFP SCOPE – Biometric Verification at Food/Cash Distributions (DRC)', AI Hub AI Tracker, case COD-001. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/COD-001 [Accessed: 1 April 2026].

Change History

Updated 31 Mar 2026, 06:35
by system (system)
Created 30 Mar 2026, 08:38
by v2-import (import)