MACHINE LEARNING MEETS TAX FRAUD: INSIGHTS FROM SLOVAKIA

• Authors: Baumӧhl Eduard , Antol Roderik , Výrost Tomáš , Bačo Tomáš
• Languages of publication: EN

Abstracts

EN

One of the most intriguing topics in the field of corporate finance is the detection of tax fraud. We consider a unique dataset of outcomes from Slovak tax authority audits, obtaining valuable insights into verified instances of tax manipulation and avoiding the misclassification problem that is common in this stream of literature. We apply artificial neural networks, random forests, XGBoost, and support vector machines to verify the extent to which we can classify tax manipulators on the basis of publicly available financial statement indicators. Our results show that the XGBoost model demonstrated the highest effectiveness, achieving an F1 score of 0.75 in the full sample, slightly lower scores within the industry groups, and excellent results in sector A – Agriculture, with an F1 score of 0.85. Our results indicate that the use of nowadays commonly known machine learning methods along with standard financial variables can provide a useful tool for tax fraud detection and, as such, can contribute to higher efficiency of tax audits.

Keywords

EN

TAX FRAUDS; MACHINE LEARNING; EARNINGS MANAGEMENT; SLOVAKIA

• Publisher: Institute of Slovak and World Economics and Institute for Forecasting, Slovak Academy of Sciences
• Journal: Ekonomický časopis (Journal of Economics)
• Year: 2025
• Volume: 73
• Issue: 5 - 6
• Pages: 181 – 209

Contributors

author

Baumӧhl Eduard

• University of Economics, Faculty of Commerce, Dolnozemská cesta 1, 852 35 Bratislava, Slovak Republic

• https://orcid.org/0000-0002-5444-7348

author

Antol Roderik

• https://orcid.org/0009-0009-7945-3005

author

Výrost Tomáš

• https://orcid.org/0000-0002-8384-5

author

Bačo Tomáš

Identifiers

DOI

https://doi.org/10.31577/ekoncas.2025.05-06.01