evidoria

← Back to browse

Good practice Imported

DGII's AI Anomaly Detector — Flagging Irregular Patterns in the Dominican Republic's Billion-Invoice E-Invoicing System

Dominican Republic · Santo Domingo · See the Dominican Republic profile · See the Santo Domingo profile

Evidence: Descriptive / self-reported Top 83% 40/100 · Ask Evidence Copilot about this practice

The Dominican Republic's tax authority added an AI anomaly detector to its e-invoicing system, which has processed over 1 billion electronic tax receipts. It flags simulated or unusual invoicing patterns for audit, but no independent fraud-catch figures are published.

1,000,000,000+
Electronic fiscal receipts processed (e-CF) (2023–Aug 2025)
8,000+
Registered electronic invoicing emitters and receivers (as of Aug 2025)
DGII's AI Anomaly Detector — Flagging Irregular Patterns in the Dominican Republic's Billion-Invoice E-Invoicing System

Details

Maturity
Scaling
Promoter
Dirección General de Impuestos Internos (DGII)
Period
2023–present (AI detector added 2025)
Keywords
taxation, fraud detection, digital government, e-invoicing

Context

The Dominican Republic made electronic invoicing mandatory nationwide under Law 32-23 (effective May 2023). By August 2025, the tax authority DGII had processed over 1 billion electronic fiscal receipts (e-CF) from more than 8,000 registered electronic emitters and receivers. In 2025, DGII added an AI-based 'Detector de Anomalías en Facturación Electrónica' on top of this dataset, which analyses invoicing patterns to flag simulated transactions, atypical volumes and other fiscal-risk signals for human inspectors to review.

Implementation
Indicative cost
Medium (€50k–€500k)
Time to results
Short (< 1 year)
Staffing & skills
DGII Technology Manager (technical/AI oversight), Fiscal inspectors (review flagged cases)

Conditions for success

  • Mature underlying e-invoicing dataset (mandatory nationwide since Law 32-23, 2023)
  • Integration with existing audit/inspection workflow
  • Ongoing tuning of anomaly-flagging patterns as fraud tactics evolve

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