evidoria

← Back to browse

Good practice Imported

Uzbekistan Tax Committee's Real-Time AI Risk-Scoring for Electronic VAT Invoices

Uzbekistan · Tashkent · See the Uzbekistan profile · See the Tashkent profile

Evidence: Descriptive / self-reported Top 32% 67/100 · Ask Evidence Copilot about this practice

Uzbekistan's Tax Committee, with IMF support, built a real-time AI risk-scorer for mandatory e-invoices, red-flagging suspected fraud; its existing analytics already found 27 shell firms issuing 3.9 trillion UZS in fictitious invoices in just Q3 2025.

27 companies
Fictitious e-invoices identified (Q3 2025)
3.9 trillion UZS
Value of fictitious invoices (Q3 2025)
706 billion UZS
VAT wrongly credited (Q3 2025)
Uzbekistan Tax Committee's Real-Time AI Risk-Scoring for Electronic VAT Invoices

Details

Maturity
Pilot
Promoter
State Tax Committee of the Republic of Uzbekistan, with IMF technical assistance
Period
2025–2026
Keywords
tax administration, VAT compliance, fraud detection

Context

Uzbekistan's State Tax Committee, with IMF technical assistance, built a real-time risk-scoring system for mandatory e-invoices (Uzasbo Faktura/ESF, required since 2020), rating each invoice green (low-risk) or red (high-risk).

Results

In Q3 2025 alone, the Committee's existing analytics identified 27 companies that issued fictitious e-invoices worth 3.9 trillion UZS, of which 706 billion UZS in VAT had already been wrongly credited.

Conclusions

The new automated scoring layer entered pilot on 22 December 2025 with no enforcement during the pilot; officials estimate ~10% of invoices will be flagged high-risk, and full enforcement begins 1 January 2026.

Implementation
Indicative cost
Medium (€50k–€500k)
Time to results
Short (< 1 year)
Staffing & skills
State Tax Committee analysts, IMF technical assistance team

Conditions for success

  • a deliberate no-enforcement pilot period to calibrate the model before live consequences

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