Explainable Graph Neural Fraud Detection for Real-Time Digital Payment Networks Using Temporal Neighborhood Inference
Fintech Innovation Journal · 12.08.2026 · 2 (3) · 192
DOI: 10.63913/ftij.v2i3.33 ↗Kurz gefasst
Fachartikel in der Zeitschrift Fintech Innovation Journal, online erschienen am 12.08.2026. Verfasst von Raylen Mintarya.
Abstract (Originalsprache)
Real-time fraud detection in digital payments must balance high detection accuracy, strict latency constraints, and audit-ready explanations. This study proposes an explainable graph-based framework that models payment activity as a temporal, attributed interaction network and performs transaction-level (edge) risk scoring using bounded K-hop neighborhoods within a sliding time window. Evaluation was conducted under a time-ordered protocol to prevent label leakage and to reflect delayed fraud confirmation. The dataset exhibits extreme class imbalance typical of production payment systems (fraud prevalence
Zitieren
APA
Mintarya, R. (2026). Explainable Graph Neural Fraud Detection for Real-Time Digital Payment Networks Using Temporal Neighborhood Inference. Fintech Innovation Journal, 2(3), 192. https://doi.org/10.63913/ftij.v2i3.33
Vancouver
Mintarya R. Explainable Graph Neural Fraud Detection for Real-Time Digital Payment Networks Using Temporal Neighborhood Inference. Fintech Innovation Journal. 2026;2(3):192. doi:10.63913/ftij.v2i3.33
BibTeX
@article{Mintarya2026,
author = {Mintarya, Raylen},
title = {Explainable Graph Neural Fraud Detection for Real-Time Digital Payment Networks Using Temporal Neighborhood Inference},
journal = {Fintech Innovation Journal},
year = {2026},
volume = {2},
number = {3},
pages = {192},
doi = {10.63913/ftij.v2i3.33}
}
EUVIMED