International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 146 - Issue 12 |
Published: Jul 2016 |
Authors: Assem Khalaf Ahmed Allam El-Din, Nashaat El Khamesy |
![]() |
Assem Khalaf Ahmed Allam El-Din, Nashaat El Khamesy . Data Mining Techniques for Anti-Money Laundering. International Journal of Computer Applications. 146, 12 (Jul 2016), 28-33. DOI=10.5120/ijca2016910953
@article{ 10.5120/ijca2016910953, author = { Assem Khalaf Ahmed Allam El-Din,Nashaat El Khamesy }, title = { Data Mining Techniques for Anti-Money Laundering }, journal = { International Journal of Computer Applications }, year = { 2016 }, volume = { 146 }, number = { 12 }, pages = { 28-33 }, doi = { 10.5120/ijca2016910953 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2016 %A Assem Khalaf Ahmed Allam El-Din %A Nashaat El Khamesy %T Data Mining Techniques for Anti-Money Laundering%T %J International Journal of Computer Applications %V 146 %N 12 %P 28-33 %R 10.5120/ijca2016910953 %I Foundation of Computer Science (FCS), NY, USA
We use a data mining framework that is based on evaluating four types of neural networks, and that uses dataobtained from regular records collected from banks, to produce a classification conclusion on "who are money laundering and who are not". This will be attained by evaluating the outcomes of various types of neural networks, namely, the Multi-Layer Perceptron Neural Network (MLP), Probabilistic Neural Network (PNN), Radial Basis Function (RBF) and Linear Neural Network (LNN). Then compare these outcomes with standard statistical results. Creating by this an accurate and fast basis for decision-making which otherwise could take days or even months.