Machine Learning Meets Tax Fraud: Insights from Slovakia

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F25%3A00143624" target="_blank" >RIV/00216224:14560/25:00143624 - isvavai.cz</a>

Výsledek na webu

<a href="https://journals.savba.sk/index.php/ekonomickycasopis/article/view/3902" target="_blank" >https://journals.savba.sk/index.php/ekonomickycasopis/article/view/3902</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.31577/ekoncas.2025.05-06.01" target="_blank" >10.31577/ekoncas.2025.05-06.01</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Machine Learning Meets Tax Fraud: Insights from Slovakia

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Machine Learning Meets Tax Fraud: Insights from Slovakia

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50200 - Economics and Business

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

EKONOMICKY CASOPIS

ISSN

0013-3035

e-ISSN

0013-3035

Svazek periodika

73

Číslo periodika v rámci svazku

5-6

Stát vydavatele periodika

SK - Slovenská republika

Počet stran výsledku

29

Strana od-do

181-209

Kód UT WoS článku

001632546300001

EID výsledku v databázi Scopus

2-s2.0-105018923991