evidoria

← Back to browse

Good practice Imported

MEVA — Turkey's Spatial Data System Catching Undeclared Property Income

Türkiye · Ankara · See the Türkiye profile · See the Ankara profile

Evidence: Observational / pre–post Top 24% 73/100 · Ask Evidence Copilot about this practice

Turkey's Revenue Administration used a GIS-based, AI-assisted value-matching system to scan over 16,000 properties in 2025, flag 9,150 owners for unexplained value gaps, and recover 113.9 million lira from voluntary compliance.

16,000+
Property transfers scanned (2025)
9,150
Owners queried over value discrepancies (2025)
2,475
Taxpayers voluntarily correcting declarations (2025)
113.9 million lira
Additional stamp duty recovered (2025)
5.9 billion lira
Adjusted property value underlying recovery (2025)
81 directorates
Provincial tax directorates covered (2025)
MEVA — Turkey's Spatial Data System Catching Undeclared Property Income

Details

Maturity
Scaling
Promoter
Revenue Administration (Gelir İdaresi Başkanlığı), Ministry of Treasury and Finance
Period
2025–present
Keywords
tax administration, property valuation, GIS and spatial analytics, compliance

Context

MEVA (Mekânsal Veri Analiz Sistemi, 'Spatial Data Analysis System') is operated by Turkey's Revenue Administration under the Ministry of Treasury and Finance. It layers property deeds, tax filings, bank credit records, real-estate listings and appraisal reports to estimate a property's true market value and compare it against the price declared for deed and stamp-duty purposes.

Activities

Specialist tax-policy commentary describes the system as using 'various algorithms' and, for large data volumes, 'artificial intelligence-supported modeling' for clustering, forecasting and risk scoring. Deployed across all 81 provincial tax directorates in 2025, the system scanned property transfers and requested explanations from owners with flagged value discrepancies.

Results

MEVA scanned more than 16,000 property transfers, requested explanations from 9,150 owners over value discrepancies, and recorded 2,475 taxpayers voluntarily correcting their declarations — paying 113.9 million lira in additional stamp duty on 5.9 billion lira of adjusted property value.

Conclusions

Finance Minister Mehmet Şimşek has announced plans to extend MEVA to detect unreported rental income. No published source describes an independent appeals process for taxpayers who are flagged.

Implementation
Indicative cost
Medium (€50k–€500k)
Time to results
Long (> 3 years) — Deployed across all 81 provincial tax directorates within 2025, its first reported year of operation; further expansion to rental-income detection has been announced.
Staffing & skills
Revenue Administration (Gelir İdaresi Başkanlığı), Ministry of Treasury and Finance (Turkey), Provincial tax directorates (all 81)

Conditions for success

  • Integration of multiple existing datasets (deeds, tax filings, bank credit records, real-estate listings, appraisals)
  • AI-supported modeling for clustering, forecasting and risk scoring at scale
  • Nationwide administrative rollout across all provincial tax directorates

Common failure modes

  • No published independent appeals process for taxpayers who are flagged
  • No public technical audit of the algorithm has been published

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