evidoria

← Back to browse

Good practice

ERA, RESNET & Smart Scanning — Madagascar Customs' AI-Powered Risk Analysis and Cargo Screening

Madagascar · Antananarivo · See the Madagascar profile

Madagascar's customs authority, an IMF pilot country for AI in customs, credits its AI risk-scoring tool ERA with a 68% year-on-year revenue jump in January 2025 — a real, officially cited figure, but a single self-reported month with no independent audit or cost data published.

ERA, RESNET & Smart Scanning — Madagascar Customs' AI-Powered Risk Analysis and Cargo Screening

Details

Promoter
Direction Générale des Douanes de Madagascar (DGD), with IMF technical assistance
Period
AI tools in active use by January 2025; IMF technical-assistance mission April 2025; regional scale-up planned through 2029
Keywords
customs, dynamic risk analysis, computer vision, revenue collection, e-government

Description

Madagascar's Direction Générale des Douanes (DGD, the national customs authority) has deployed three AI-driven tools inside its border-control operations: ERA (Enhanced Risk Assessment), a dynamic risk-analysis engine that scores shipments for inspection targeting; RESNET, an automated image-analysis system for reading X-ray and scanner imagery; and Smart Scanning, an upgraded container- and cargo-scanning layer. Customs officials describe Madagascar as "the first public institution to adopt artificial intelligence" in the country's public sector.

The clearest published result concerns ERA: customs officials reported that in January 2025 the tool helped drive a 68% year-on-year increase in customs revenue compared with January 2024. Director General Lainkana Zafivanona Ernest cited the figure publicly at a technology conference at Ankatso in Antananarivo on 6 March 2025, attended by more than 2,500 students and academics from Durham University, the London School of Economics and Universitas Airlangga.

The International Monetary Fund has named Madagascar its pilot country in Africa for integrating AI into customs administration. Two IMF specialists, Victor Budeau and François Chastel, began an on-site technical-assistance mission in Antananarivo on 24 April 2025 to intensify training on AI-based risk analysis. The DGD's stated ambition is to extend these tools to additional control sectors and to share its experience regionally by 2029.

The 68% figure is a genuine, officially cited result, but it is a single self-reported month-on-month comparison from the customs authority itself, not an independently audited statistic, and no cost, fraud-detection-rate, or false-positive data has been published alongside it. There is also no public description of an appeals process, an independent oversight body, or a data-protection framework governing the risk-scoring model — worth flagging as an evidence gap even in an otherwise substantive, multi-sourced deployment.

Read the full analysis: https://www.douanes.gov.mg/douane-malagasy-pionniere-de-lintelligence-artificielle-dans-le-secteur-public/

Implementation

Implementation detail (cost, timeline, staffing, conditions for success) is not yet available for this practice.

Data sources

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

Attachments

Similar practices you may find useful