evidoria

← Back to browse

Good practice Imported

ARAS — Azerbaijan Customs' AI Risk-Corridor System Reports a 58% Cut in Border-Crossing Time

Azerbaijan · Baku · See the Azerbaijan profile · See the Baku profile

Evidence: Descriptive / self-reported Top 51% 60/100 · Ask Evidence Copilot about this practice

Azerbaijan Customs built ARAS, a machine-learning risk system sorting shipments into green/yellow/blue/red corridors. The customs chief reported a 58% cut in border-crossing time and 20% fewer inspections after one year — self-reported, not independently audited.

-58%
Average border-crossing time change (first year (Jan 2024-Jan 2025))
-15%
Clearance time change (first year)
-20%
Physical inspections change (first year)
ARAS — Azerbaijan Customs' AI Risk-Corridor System Reports a 58% Cut in Border-Crossing Time ARAS — Azerbaijan Customs' AI Risk-Corridor System Reports a 58% Cut in Border-Crossing Time

Details

Maturity
Established
Promoter
State Customs Committee of the Republic of Azerbaijan
Period
January 2024–present
Keywords
customs, border management, risk analysis, trade facilitation

Context

The State Customs Committee of Azerbaijan built and launched the Automated Risk Analysis System (ARAS) in January 2024. ARAS uses machine-learning algorithms to score the risk profile of each trader, carrier, and shipment from pre-submitted data, then assigns it to a green, yellow, blue, or red clearance corridor that determines how much physical inspection it receives. The Committee has since begun rolling out an upgraded 'ARAS Pro' version, indicating continued institutional investment.

Results

Speaking at a Customs-Business Forum in Baku on 17 December 2024, State Customs Committee Chairman Shahin Bagirov said that in ARAS's first year, average border-crossing time fell 58%, clearance time fell 15%, and the number of physical inspections fell 20%. These figures are self-reported by the customs chief and were not accompanied by an independently audited before/after methodology; independent Azerbaijani outlet AzerNews reported the same figures from his remarks.

Implementation
Indicative cost
Medium (€50k–€500k) — No budget figure is published; classified as medium cost for a nationwide in-house risk-scoring system now in a second ('Pro') version.
Time to results
Short (< 1 year) — Built and launched nationwide in January 2024, with an upgraded 'Pro' version rolled out within about a year.
Staffing & skills
State Customs Committee of Azerbaijan specialists (built in-house)

Conditions for success

  • Risk scoring from pre-submitted trader/carrier/shipment data
  • Named accountable chairman reporting results publicly
  • Continued institutional investment (ARAS Pro upgrade)

Common failure modes

  • Impact figures are self-reported by the customs chief with no independently audited before/after methodology
  • Underlying scoring criteria and any appeal process for misclassified shipments are not disclosed

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