Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/251240
Title: An Effective Algorithm on Anti Money Laundering Compliance Using Data Mining Techniques
Researcher: Vikas Jayasree
Guide(s): Siva Balan R.V
Keywords: Engineering and Technology,Computer Science,Automation and Control Systems
University: Noorul Islam Centre for Higher Education
Completed Date: 22/12/2016
Abstract: ABSTRACT newlineData mining schemes are mainly employed for prevention and detection of newlineMoney Laundering (ML) frauds. Data mining methods have the capability of detecting newlineML fraud in banking because it easily identifies and detects the risk of fraud in ML. ML newlineidentification uses the time series data and recognizes one-to-many and many-to-one newlinerelationship between transactions to discover the susceptible accounts. Maintaining newlineregulatory risk rate and providing security for financial organizations has become the newlinekey for money laundering. newlineExisting research work is conducted on financial fraud detection framework newlinewhich classifies the data mining tasks and solves the problems associated with newlinefraudulent discovery. However, financial fraud detection does not concentrate on newlinepractical ML banking standards and solutions. Also, Joint Threshold Administration newlineequally manages the banking databases which make use of kernel function. But, the ML newlinediscovery with the help of database information is not performed efficiently to achieve newlinereliable transaction and response. newlineAn acceptable transaction occurs between the security and performance in newlinefinancial organization. Security though enhances the transaction but it avoids ML based newlinesecurity failure detection. However, in several legal and regulatory systems, the term newlineML has developed into combined with other types of financial crime, and it also used to newlineinvolve misuse of the financial system. Crime identification has become significant and newlineextensive due to the enormous data availability on the Web and this has resulted for the newlineperpetrators to prevent their original identities. newlineData mining methods have the potentiality for detecting ML fraud in banking as newlinethey utilize history of fraud to build models, which recognize and distinguish the risk of newlinefraud. Several data mining approaches were presented that involved anomaly detection newlineusing principal component analysis and self organizing map. But nevertheless, with high newlinedimension data, they pose serious issues. newlineii newlineThe proposed Probabilistic Relationa
Pagination: 132
URI: http://hdl.handle.net/10603/251240
Appears in Departments:Department of Computer Applications

Files in This Item:
File Description SizeFormat 
acknowledgement.pdfAttached File7.18 kBAdobe PDFView/Open
certificate.pdf24.04 kBAdobe PDFView/Open
chapter-iii.pdf377.65 kBAdobe PDFView/Open
chapter-ii.pdf176.58 kBAdobe PDFView/Open
chapter-i.pdf152.59 kBAdobe PDFView/Open
chapter-iv.pdf335.39 kBAdobe PDFView/Open
chapter-vii.pdf9.59 kBAdobe PDFView/Open
chapter-vi.pdf314.84 kBAdobe PDFView/Open
chapter-v.pdf521.95 kBAdobe PDFView/Open
references.pdf376.95 kBAdobe PDFView/Open
title page.pdf22.62 kBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.