Deep Learning-Based Anomaly Attribution for Financial Transaction Compliance
International Journal of Engineering & Extended Technologies Research · 22.02.2023 · 5 (01)
DOI: 10.15662/ijeetr.2023.0501007 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Engineering & Extended Technologies Research, online erschienen am 22.02.2023. Verfasst von Subba Nelakudhiti und 2 weiteren Autor:innen.
Abstract (Originalsprache)
The current paper examines the application of operational models based on deep learning to identify anomalies during financial transactions and attribution to improve the adherence costs to regulatory measures like the Anti-Money Laundering (AML) and Know Your Customer (KYC). The complex frauds usually do not work well on a traditional system of rules that could be detected in real time. Using Convolutional neural networks (CNNs), Long short-term memory networks (LSTMs), and autoencoders, deep learning models are applicable to detect and warn suspicious transactions based on the historical patterns of transactions. This paper will illustrate that deep learning- based anomaly detection will enhance detection accuracy, minimize false positives, and guarantee compliance within the banking, fintech, and credit card transactions sectors.
Zitieren
APA
Nelakudhiti, S., Thonduru, R., & Arikatla, R. R. (2023). Deep Learning-Based Anomaly Attribution for Financial Transaction Compliance. International Journal of Engineering & Extended Technologies Research, 5(01). https://doi.org/10.15662/ijeetr.2023.0501007
Vancouver
Nelakudhiti S, Thonduru R, Arikatla RR. Deep Learning-Based Anomaly Attribution for Financial Transaction Compliance. International Journal of Engineering & Extended Technologies Research. 2023;5(01). doi:10.15662/ijeetr.2023.0501007
BibTeX
@article{Nelakudhiti2023,
author = {Nelakudhiti, Subba and Thonduru, Rajesh and Arikatla, Rajasekhar Reddy},
title = {Deep Learning-Based Anomaly Attribution for Financial Transaction Compliance},
journal = {International Journal of Engineering & Extended Technologies Research},
year = {2023},
volume = {5},
number = {01},
doi = {10.15662/ijeetr.2023.0501007}
}
EUVIMED