AI suggests tariff codes and flags undervaluation against reference price databases
- Who we serve
- Governments and Public Agencies
- Category
- PFM, Tax & Customs
- Value
- Revenue
- Human role
- Human approves every decision
- Maturity
- B-READY topics
- International Trade
The problem
Without HS classification & valuation assistance, customs authorities make these calls on averages and instinct, because tax returns, invoices, customs declarations, third-party and financial data are not joined up, and the value in the data goes uncaptured.
How it works
HS classification & valuation assistance - AI suggests tariff codes and flags undervaluation against reference price databases. It draws on tax returns, invoices, customs declarations, third-party and financial data and is typically owned by customs authorities. Where the human comes in: customs authorities review and approve before any action affects a person, a payment or a case; the AI flags, ranks and drafts. It is scaled at leading organisations and piloted elsewhere; examples include Brazil SISAM (Receita Federal); Korea Customs Service.
Where the human comes in
Customs authorities review and approve before any action affects a person, a payment or a case; the AI flags, ranks and drafts
What it needs
tax returns, invoices, customs declarations, third-party and financial data
What to plan for
Reference price data quality
In the field
Brazil SISAM (Receita Federal); Korea Customs Service
UNCTAD ASYCUDA (2025); WCO
Public deployments by other organizations, listed for context. Not Sphere projects.