Statistical analysis of money laundering risks with public financial data sets

Purpose- This study statistically examines money laundering (ML) risk in Türkiye over 2015-2024 using public financial datasets. We conceptualize ML not only as a criminal phenomenon but also as a structural threat to macroeconomic stability, fiscal discipline, and the integrity of financial intermediation. The analysis integrates official data from the Central Bank of the Republic of Türkiye (CBRT), Ministry of Treasury and Finance, Banking Regulation and Supervision Agency (BRSA), Financial Crimes Investigation Board (MASAK), Turkish Statistical Institute (TurkStat), and the Financial Action Task Force (FATF). Methodology- Two dependent measures are employed: (i) a Money Laundering Index (MLI) constructed from shadow economy, cash intensity, tax revenue shortfall, financial depth, and FATF alignment; and (ii) Suspicious Transaction Reports (STRs) as a system-level signal of risk perception and supervisory capacity. Explanatory variables include FATF Compliance Score, cash density, tax collection gap, GDP growth, inflation, interest rate, financial-institution size, and compliance cost. We estimate correlations and regression models (time-series/panel formulations as permitted by data), supported by robustness checks, to assess directional associations between ML proxies and macro-financial indicators. Findings- Results indicate that higher ML intensity is negatively associated with financial stability and fiscal control: greater cash intensity and a wider tax gap co-move with higher STR volumes and MLI values; ML pressures complicate monetary control and are consistent with heightened volatility in interest and inflation dynamics. Conversely, improvements in FATF compliance are associated with lower ML risk proxies and reduced STR intensity after controlling for business-cycle conditions-albeit with non-trivial compliance costs borne by financial institutions (e.g., KYC, reporting, internal audit). The findings highlight the strategic value of public-data analytics for early risk detection, scenario monitoring, and the calibration of risk-based supervision. Conclusion- Policy implications are threefold: (1) strengthen data governance and routine publication of high-frequency AML-relevant indicators; (2) advance risk-based oversight using composite indices (MLI) that fuse macro-fiscal and sectoral signals; and (3) sustain FATF-aligned reforms while optimizing the distribution of compliance burdens. Limitations stem from proxy measurement (no direct ML dataset), external shocks (e.g., COVID-19), and annual granularity for select variables; hence, results support analytical rather than statistical generalization. Overall, the paper translates public finance data into actionable AML intelligence and a scalable evidence base for policy design. Keywords: Anti-Money Laundering (AML); Illicit Financial Flows (IFFs); Shadow/Informal Economy; Suspicious Transaction Reports (STRs); Public Data Analytics JEL Codes: O17, H26, G28