The Fraud Detection Optimization in Open Metaverse Blockchain Transactions: Case study based on ML-GRU Neural Networks

Authors

  • Habib Zouaoui University of Relizane
  • Ahmed Louzani University of Blida1
  • Meryem-Nadjat Naas University of Relizane

DOI:

https://doi.org/10.7190/fintaf.v3i1.512

Keywords:

Fraud Prevention, blockchain, A Deep learning approach, financial decision-making

Abstract

The study explores anomaly detection in blockchain transactions within the Open Metaverse Our proposed system  aims to achieve three critical objectives: detecting fraudulent transactions by identifying suspicious patterns and anomalies, assessing transaction risks through the categorization of risk profiles, and analyzing user behavior to enhance security, personalize financial services, and improve user experiences. Through the meticulous classification of transactions for fraud detection, risk assessment, and user behavior analysis, this project aspires to bolster the security and transparency of Open Metaverse finance, setting the stage for a safer and more user-centric virtual financial landscape.

DATASET: -The dataset comprises 78,600 entries, each depicting a transaction within the metaverse. These entries are characterized by various attributes including the Timestamp, Hour of the Day, Sending and Receiving Addresses, Transaction Amount, Type, Location Region, and IP Prefix, along with user-centric data like Login Frequency, Session Duration, Purchase Patterns, Age Group, Risk Score, and potential Anomalies.

Downloads

Published

2026-02-26

Issue

Vol. 3 No. 1 (2025): FinTech and AI in Finance (FinTAF)

Section

Articles.

License

Copyright (c) 2026 Habib ZOUAOUI, Ahmed LOUZANI, Meryem-Nadjat NAAS

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

  1. It is the responsibility of authors to ensure that permissions to reproduce any kind of third party material are obtained from copyright holders prior to the article being submitted for publication.
  2. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under the CC-BY licence .
  3. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.