Dynamic Calibration of Decision Thresholds for Financial Anomaly Detection
Journal of Global Information Management · 23.12.2025 · 33 (1) · 1-25
DOI: 10.4018/jgim.395852 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Global Information Management, erschienen am 23.12.2025. Verfasst von Anzhong Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Digital payment channels have expanded quickly, reshaping transaction flows while opening new avenues for fraud. Isolation Forest (IF) remains attractive for unsupervised screening, yet deployments that rely on a fixed anomaly-score threshold deteriorate when traffic shifts or is actively manipulated. The authors present a Temporal-Attention Isolation Forest with Dynamic Calibration (TA-IFDC) that treats threshold selection as an adaptive component rather than a static post-processing step. The method monitors the evolving distribution of IF scores in streaming mode and updates the decision boundary online, while a lightweight temporal-attention module encodes short-range dependencies across consecutive transactions. Together, these pieces allow the detector to adjust to drift without sacrificing precision during stable periods.
Zitieren
APA
Huang, A., Wang, Y., Zhou, P., Zhang, X., Tsai, S., & Chen, L. (2025). Dynamic Calibration of Decision Thresholds for Financial Anomaly Detection. Journal of Global Information Management. https://doi.org/10.4018/jgim.395852
Vancouver
Huang A, Wang Y, Zhou P, Zhang X, Tsai S, Chen L. Dynamic Calibration of Decision Thresholds for Financial Anomaly Detection. Journal of Global Information Management. 2025. doi:10.4018/jgim.395852
BibTeX
@article{Huang2025,
author = {Huang, Anzhong and Wang, Yuanyuan and Zhou, Ping and Zhang, Xin and Tsai, Sangbing and Chen, Lin},
title = {Dynamic Calibration of Decision Thresholds for Financial Anomaly Detection},
journal = {Journal of Global Information Management},
year = {2025},
doi = {10.4018/jgim.395852}
}
EUVIMED