AI Risk Scoring for Courier Low Value Shipments

Border & Immigration · Risk Assessment & Triage

What it collects

Operational data

Anonymized data

Cargo shipment data from CBSA covering courier packages in the low value shipments stream — including shipment manifest details such as commodity descriptions, declared values, origin countries, and shipper/consignee routing information.

Canada AI Register — entry 2526-CBSA-ASFC-007

Operational data

Anonymized data

Enforcement data from CBSA — records of prior enforcement actions, seizures, and compliance outcomes related to courier shipments, used as labeled training and evaluation data for the probabilistic models.

Canada AI Register — entry 2526-CBSA-ASFC-007

Run by: Canada Border Services Agency (CBSA)
Where: No fixed location
Kept: Not stated by the Helpful Places.
Shared with: Accountable organization
Your copy: You cannot see the data it holds about you. What you can do

What it is for

Border & Immigration

Risk Assessment & Triage

This system uses machine learning and probabilistic modelling to assign risk scores to packages entering Canada through the Courier Low Value Shipments stream. It is used by Canada Border Services Agency employees to assess which packages may warrant further examination. The system is currently in development and does not process personal information. Members of the public are not informed when this scoring is applied to their shipments.

What it collects and what happens to it

Data taken in

Operational data

Anonymized data

Cargo shipment data from CBSA covering courier packages in the low value shipments stream — including shipment manifest details such as commodity descriptions, declared values, origin countries, and shipper/consignee routing information.

Canada AI Register — entry 2526-CBSA-ASFC-007

Operational data

Anonymized data

Enforcement data from CBSA — records of prior enforcement actions, seizures, and compliance outcomes related to courier shipments, used as labeled training and evaluation data for the probabilistic models.

Canada AI Register — entry 2526-CBSA-ASFC-007

Processing

Classification & Prediction

Probabilistic modelling techniques assess the risk level of each package and output a risk score or classification. Machine learning models are trained on historical cargo and enforcement data to predict which shipments are likely to be of concern.

Canada AI Register — entry 2526-CBSA-ASFC-007

What it does

Deciding (Analytical AI)

Human decides

Generates a probabilistic risk score for each courier package. GC employees (primary users) review the scores and make decisions about whether to act on them; the system is advisory rather than determinative.

Canada AI Register — entry 2526-CBSA-ASFC-007

Outputs

A recommendation or prediction

Anonymized data

A risk score for each courier package, indicating the probability that the shipment warrants further examination or enforcement action. Scores are advisory — final decisions are made by CBSA employees.

Canada AI Register — entry 2526-CBSA-ASFC-007

Run by

Canada Border Services Agency (CBSA)

The Canada Border Services Agency (CBSA) is the accountable government department developing and deploying this risk-scoring system for courier low value shipments at the Canadian border.

Canada AI Register — entry 2526-CBSA-ASFC-007

Built by

Government of Canada

The system was developed by the Government of Canada. No external vendor is identified in the register entry.

Canada AI Register — entry 2526-CBSA-ASFC-007

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization

Risk scores produced by the system are available to GC employees (primary users) within the Canada Border Services Agency for the purpose of making shipment examination decisions.

Canada AI Register — entry 2526-CBSA-ASFC-007

Not available to me

Risk scores are not made available to the public, importers, or courier recipients. The register confirms AI use is not disclosed to affected parties, and no public access mechanism is described.

Canada AI Register — entry 2526-CBSA-ASFC-007

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data: Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data: Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data: The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides: This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes: This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous: This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

Right to Be Informed of AI UseThe register explicitly states that AI use is NOT disclosed to users or affected parties. Senders and recipients of courier packages are not informed that an AI risk-scoring system has been applied to their shipments. There is no stated mechanism for members of the public to learn whether this system has been used in relation to their package.

Risks and safeguards

Civil liberties harmAutomated risk scoring at the border may disproportionately flag shipments associated with particular origins or commodities, creating discriminatory inspection patterns without public awareness. The register notes that AI use is not disclosed to affected parties.Safeguard: The system is described as advisory (GC employees make final decisions), and the register states no personal information is involved. However, no specific bias auditing, transparency, or redress mechanisms are described in the register entry; these gaps represent residual risks for affected shippers.