Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: VELIDI, SRIRAM CHOWDARY
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2025
Schlagworte:
Online-Zugang:https://doi.org/10.5281/zenodo.15066269
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • <p>Financial institutions suffer substantial losses due<br>to fraudulent online transactions. Traditional fraud detection<br>methods often fail to identify evolving fraud patterns due to<br>dataset imbalance and high false negative rates. This paper<br>proposes an adaptive fraud detection system integrating a valueat-risk (VaR) metric with machine learning techniques. The<br>system uses historical simulation to estimate potential fraudrelated losses and employs K-Nearest Neighbors (KNN) to classify<br>fraudulent transactions. The proposed approach enhances fraud<br>detection accuracy while minimizing false negatives, providing an<br>effective fraud prevention framework for financial institutions.</p>