evidoria

← Back to browse

Good practice

Canada Revenue Agency — AI-driven detection of unwarranted GST/HST refund claims

Canada · Ottawa · See the Canada profile

Canada Revenue Agency uses ML and AI-powered analytics to detect unwarranted GST/HST refund claims. Since 2017–18, over C$1.1 billion in carousel-scheme fraud identified; compliance activities now flag over C$1.5 billion in suspicious refund claims annually.

C$1.1 billion+
Unwarranted carousel-scheme refunds identified since 2017–18 (2017–18 to present)
C$1.5 billion+
Suspicious refund claims flagged annually (2023–24)
C$42 million
Amount exceeding Budget 2021 target (2023–24)
C$425.7 million
Total compliance investment (Budgets 2016/2017/2018/2021)

Details

Maturity
Established
Promoter
Canada Revenue Agency (CRA) / Agence du revenu du Canada
Period
2018-present
Keywords
tax compliance, machine learning, GST/HST fraud, carousel fraud, risk scoring, data analytics

Context

The Canada Revenue Agency uses machine learning and AI-driven risk-scoring models — cross-referencing GST/HST returns against banking, payroll, supplier-network and import/export data — to flag suspicious refund claims, particularly 'carousel' fraud, before refunds are paid; human auditors review all AI-flagged returns, and the system operates under Treasury Board's Directive on Automated Decision-Making.

Results

Since 2017–18, AI-assisted compliance activities have identified more than C$1.1 billion in unwarranted carousel-scheme refunds; by 2023–24 the system flags over C$1.5 billion annually in suspicious claims, and the CRA's 2023–24 Departmental Results Report confirms it exceeded its Budget 2021 target of identifying C$250 million in unwarranted refunds by C$42 million that fiscal year.

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.

Similar practices you may find useful