EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparative Analysis of Graph Neural Networks for Fraud Detection

Ricky Maulana Fajri, Muhammad Gald Teary, Ni Wayan Pricila Yuni Praditya

Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer · 21.05.2026 · 10 (1) · 88-98

DOI: 10.31961/93y6ve52 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer, online erschienen am 21.05.2026. Verfasst von Ricky Maulana Fajri und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting financial fraud is a complex and evolving challenge, particularly because of the relational nature of transaction data, graph sparsity, and severe class imbalance. To the best of our knowledge, this study repre-sents one of the first systematic benchmarks of five prominent Graph Neural Network (GNN) architectures, GCN, GAT, GraphSAGE, GIN, and SGCN, for fraud detection under balanced and imbalanced conditions across multiple public datasets. We explicitly evaluate the impact of the Synthetic Minority Oversampling Technique (SMOTE) on graph-based fraud detection performance, an aspect that has rarely been addressed in prior research. The comparative analysis considers predictive performance (AUC, F1-Score, Precision, Re-call) and computational efficiency to provide actionable guidance for real-world development. The experimental results show that GraphSAGE offers the best trade-off between accuracy and execution time for laten-cy-sensitive environments, while GAT’s attention mechanism supports offline, interpretability-driven analysis. These findings provide empirical evidence to inform GNN selection strategies for scalable and effective fraud detection systems.

Zitieren

APA

Fajri, R. M., Teary, M. G., & Praditya, N. W. P. Y. (2026). Comparative Analysis of Graph Neural Networks for Fraud Detection. Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer, 10(1), 88-98. https://doi.org/10.31961/93y6ve52

Vancouver

Fajri RM, Teary MG, Praditya NWPY. Comparative Analysis of Graph Neural Networks for Fraud Detection. Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer. 2026;10(1):88-98. doi:10.31961/93y6ve52

BibTeX
@article{Fajri2026,
  author = {Fajri, Ricky Maulana and Teary, Muhammad Gald and Praditya, Ni Wayan Pricila Yuni},
  title = {Comparative Analysis of Graph Neural Networks for Fraud Detection},
  journal = {Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {88--98},
  doi = {10.31961/93y6ve52}
}
Kostenlos starten →