Your Company
Home About Us Subscription Submissions Editorial Board Contact Us

Title : Internet Financial Fraud Detection based on a Distributed Big Data Approach withNode2vec

Author : Gudura Raveendrababu, Mohammad Abdul Hafeez, Shaik Abeed Basha, Indlapa Divya

Abstract :

With the use of Decision Tree and Neural Network Algorithms, anti-money-laundering systems may have their false positive rate reduced. Methods and Instruments for Research: Classification accuracy for anti-money laundering analysis is 87.75% for a recurrent neural network technique (N=10) and 69.60% for a decision tree (N=10). With a pre-test power of 0.8 and an alpha of 0.05, we calculate the sample size using GPower. Finally, when comparing mean accuracy (87.75%), Neural Networks perform better than Decision Trees. Both the accuracy and loss results are statistically significant (p>0.05) at the 0.557 level. Finally, the Mean Accuracy of Neural Networks Anti-Money Laundering Systems Is Higher Than That of Decision Trees.

[ PDF ]

Indexing

Impact Indexing 2 Google Index Indexing 4 Indexing 5

Submit Article

Email: editor@ijeri.info

International Journal of Engineering Research & Informatics (IJERI)
E-ISSN: 2348-6481

COPYRIGHT NOTICE: © 2014–2025. All rights reserved to IJERI. No part of this publication may be reproduced, stored, or transmitted in any form or by any means without prior written permission from the Publisher. Authorization to photocopy items for internal and personal use by subscribers is granted by the copyright holder. This consent does not extend to other kinds of copying such as reproduction for general distribution, resale, or use in derivative works.

DISCLAIMER: The Publisher and the Editorial Board of IJERI shall not be held responsible for any errors, inaccuracies, or consequences arising from the use of information contained in this journal. The views and opinions expressed in published articles are solely those of the respective authors and do not necessarily reflect the official policy or position of the Publisher or Editors.