Artificial Intelligence in fraud detection: textual analysis of 10-K filings
Maandblad voor Accountancy en Bedrijfseconomie · 25.04.2025 · 99 (2) · 61-71
DOI: 10.5117/mab.99.132881 ↗Kurz gefasst
Fachartikel in der Zeitschrift Maandblad voor Accountancy en Bedrijfseconomie, online erschienen am 25.04.2025. Verfasst von Florian Ketelaar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
In this paper, we investigate the potential of Artificial Intelligence (AI) in detecting fraud by analyzing linguistic indicators in 10-K filings. We analyze the word frequencies (positive, negative, uncertainty, litigious), consistency, and readability in the MD&A sections. The AI model, BERT, was trained on these factors to predict fraud, showing significant promise compared to traditional models. The findings suggest that fraudulent filings tend to have more positive words, inconsistent language, and higher readability. This highlights AI’s practical role in improving fraud detection in financial reports.
Zitieren
APA
Ketelaar, F., & Mićković, A. (2025). Artificial Intelligence in fraud detection: textual analysis of 10-K filings. Maandblad voor Accountancy en Bedrijfseconomie, 99(2), 61-71. https://doi.org/10.5117/mab.99.132881
Vancouver
Ketelaar F, Mićković A. Artificial Intelligence in fraud detection: textual analysis of 10-K filings. Maandblad voor Accountancy en Bedrijfseconomie. 2025;99(2):61-71. doi:10.5117/mab.99.132881
BibTeX
@article{Ketelaar2025,
author = {Ketelaar, Florian and Mićković, Ana},
title = {Artificial Intelligence in fraud detection: textual analysis of 10-K filings},
journal = {Maandblad voor Accountancy en Bedrijfseconomie},
year = {2025},
volume = {99},
number = {2},
pages = {61--71},
doi = {10.5117/mab.99.132881}
}
EUVIMED