evidoria

← Back to browse

Good practice Imported

EC-MADA — Madagascar's AI-Powered Digitisation of 10 Million Civil Registration Records

Madagascar · Antananarivo · See the Madagascar profile · See the Antananarivo profile

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

Studia Inc and D.IA Advisory digitised ~10 million civil registration records across 1,695 Madagascar communes for EC-MADA, using OCR/AI indexing and solar-powered mobile units. Feeds a biometric ID rollout with 6M+ enrolled by June 2026 — no independent audit exists.

~10 million
Civil registration records digitised
1,695
Communes covered
500
People mobilised for digitisation (7 months)
6 million+
Biometric ID enrolments (by June 2026)
EC-MADA — Madagascar's AI-Powered Digitisation of 10 Million Civil Registration Records

Details

Maturity
Scaling
Promoter
Studia Inc, with D.IA Advisory (Senegal), under Madagascar's national EC-MADA programme
Period
Seven-month deployment, reported May 2026
Keywords
civil registration, digital identity, OCR/AI document processing, public administration

Context

Under Madagascar's national EC-MADA programme, Studia Inc partnered with Senegal-based D.IA Advisory to digitise and index close to 10 million civil registration records from paper archives held across 1,695 communes in 11 priority regions.

Objectives

The project aimed to convert handwritten civil-registration archives into searchable digital records to feed Madagascar's biometric identity rollout, including in areas without reliable grid power or internet access.

Activities

The team used specialised OCR and AI-driven indexing to extract handwritten data, mobilising 500 people over seven months and deploying autonomous mobile units with satellite connectivity and solar power to reach remote communes.

Results

Authorities cited more than six million people enrolled in the biometric ID scheme by June 2026, up from a much smaller base before the digitisation push, according to trade-press reporting.

Conclusions

No independent audit of OCR/indexing accuracy, error rates or data-protection safeguards has been published, and the project's funding source was not disclosed in available sources, so the figures rest on vendor and trade-press reporting alone.

Implementation
Indicative cost
High (€500k–€5M)
Time to results
Medium (1–3 years)
Staffing & skills
500 people mobilised for digitisation over seven months, Studia Inc (technical delivery), D.IA Advisory (Senegal, technical partner)

Conditions for success

  • autonomous mobile units with satellite connectivity and solar power for areas without grid/internet
  • coordination across 1,695 communes in 11 priority regions
  • OCR/AI indexing tuned to handwritten archival records

Common failure modes

  • no independent audit of OCR/indexing accuracy or error rates
  • no published data-protection safeguards
  • funding source not disclosed

Where it fits

Governance type
national government programme with private vendors
Scale
national
Income level
low-income

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.

Attachments

Similar practices you may find useful