Gespeichert in:
| 1. Verfasser: | |
|---|---|
| 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>