Tax fraud & evasion detection (e-invoicing / VAT network analytics)
ML over invoice graphs, e-invoicing and third-party data flags evasion, fake invoices and VAT carousel fraud
- Who we serve
- Governments and Public Agencies
- Category
- PFM, Tax & Customs
- Value
- Risk management
- Human role
- Human approves every decision
- Maturity
- B-READY topics
- Taxation
The problem
Without tax fraud & evasion detection, revenue authorities rely on sampling and after-the-fact review, while the signals in tax returns, invoices, customs declarations, third-party and financial data sit unread, so problems surface only after the loss, incident or complaint.
How it works
Tax fraud & evasion detection (e-invoicing / VAT network analytics) - ML over invoice graphs, e-invoicing and third-party data flags evasion, fake invoices and VAT carousel fraud. It draws on tax returns, invoices, customs declarations, third-party and financial data and is typically owned by revenue authorities. Where the human comes in: revenue 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 Receita Federal e-invoice analytics; India GSTN analytics; Colombia DIAN.
Where the human comes in
Revenue 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
Explainability of selections; taxpayer rights; enabler: e-invoicing mandate
In the field
Brazil Receita Federal e-invoice analytics; India GSTN analytics; Colombia DIAN
IMF TNM 2024/006 (2024); OECD Tax Administration 3.0 (2020)
Public deployments by other organizations, listed for context. Not Sphere projects.