EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Anomaly synthesis and detection in accounting data via a generative adversarial network

Shan Zhang, Lang Zhang, Mi Wang, Ziwei Chen, Wenqian Guo

PeerJ Computer Science · 05.02.2026 · 12 · e3550

DOI: 10.7717/peerj-cs.3550 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 05.02.2026. Verfasst von Shan Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenge of anomaly detection in high-dimensional, heterogeneous accounting data, we propose multimodal fusion generative adversarial network (MF-GAN), a multimodal fusion framework that integrates synthesis and detection within a unified architecture. MF-GAN employs a dual-branch spatio-temporal generator: a temporal branch with regional residual learning to extract sequence dynamics, and a spatial branch based on convolutional networks to capture unstructured features from voucher images and associated text. A generative sample-augmentation mechanism—combining bootstrap resampling with noise injection—produces realistic anomalous samples, improving recall of rare anomaly types by 18.6% on a corpus of 180,000 real accounting records and the EnterpriseAccounting Anomaly Dataset (EAAD) dataset containing 3,200 labeled anomalies, thereby mitigating severe class imbalance. We further introduce a dynamic-weight joint optimization scheme that unifies generator and discriminator losses for collaborative training; ablating this component reduces performance by 21.4%, underscoring the importance of gradient co-training for generalization in unsupervised settings. Experimental results show that MF-GAN achieves 78.48% precision, 96.67% recall, and a 19% F1 improvement over mainstream baselines on EAAD. On the CBFAD dataset, MF-GAN attains 76.48% precision, 86.67% recall, and an 86.05% F1-score. The framework overcomes feature-extraction bottlenecks in high-dimensional time series and, through generative–discriminative co-optimization, provides an interpretable and practical pathway for financial anti-fraud supervision

Zitieren

APA

Zhang, S., Zhang, L., Wang, M., Chen, Z., & Guo, W. (2026). Anomaly synthesis and detection in accounting data via a generative adversarial network. PeerJ Computer Science, 12, e3550. https://doi.org/10.7717/peerj-cs.3550

Vancouver

Zhang S, Zhang L, Wang M, Chen Z, Guo W. Anomaly synthesis and detection in accounting data via a generative adversarial network. PeerJ Computer Science. 2026;12:e3550. doi:10.7717/peerj-cs.3550

BibTeX
@article{Zhang2026,
  author = {Zhang, Shan and Zhang, Lang and Wang, Mi and Chen, Ziwei and Guo, Wenqian},
  title = {Anomaly synthesis and detection in accounting data via a generative adversarial network},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e3550},
  doi = {10.7717/peerj-cs.3550}
}
Kostenlos starten →