Data mining in anti-money laundering field

Author:Noriaki Yasaka
Position:School of Knowledge Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, Japan
Pages:301-310
SUMMARY

Purpose This report aims to focus on how suspicious transaction report is created with data mining methods and used from the point of view of knowledge management. Design/methodology/approach This paper considers data mining versus knowledge management in the anti-money laundering (AML) field. Findings In the AML field, the information and knowledge gained are not... (see full summary)

 
FREE EXCERPT
Data mining in anti-money
laundering eld
Noriaki Yasaka
School of Knowledge Science, Japan Advanced Institute of Science and Technology,
Nomi, Ishikawa, Japan
Abstract
Purpose This report aims to focus on how suspicious transaction report is created with data mining
methods and used from the point of view of knowledge management.
Design/methodology/approach This paper considers data mining versus knowledge management in
the anti-money laundering (AML) eld.
Findings In the AML eld, the information and knowledge gained are not necessarily used for or shared
with the related shareholders. Creating and co-evolving the network of “knowledge professionals” is the
impending assignment in this industry. The rst and most important task is knowledge management in the
global AML eld.
Originality/value The report considers the creation with data mining methods and utilization from the
point of view of knowledge management.
Keywords Knowledge management, Community, Anti-money laundering, Data mining,
HS-KCSU model
Paper type General review
1. Introduction
It is difcult to determine the denition of money laundering. Latest research report of
United Nations Ofce on Drugs and Crime estimated the gure to be about 3.6 per cent of the
global GDP (2.3-5.5 per cent), equivalent to about US$2.1tn (2009), in which 2.7 per cent of
global GDP (2.3-5.5 per cent), or 1.6tn through the nancial system, is included[1]. In the
nancial system, one way of estimating money laundering is by providing a suspicious
transaction report (STR) to nancial intelligence units (FIUs). Therefore, this report focuses
on how STR is created using data mining methods and used from the viewpoint of
knowledge management.
2. Denition
2.1 Denition of money laundering and three stages of laundering cycles
Money laundering is the conversion of criminal income into assets that cannot be traced back
to the underlying crime (Reuter and Truman, 2004, p. 1). Most countries subscribe to the
denition adopted by the United Nations Convention Against Illicit Trafc in Narcotic
Drugs and Psychotropic Substances (1988) (Vienna Convention) and the United Nations
Convention Against Transnational Organized Crime (2000) (Palermo Convention) (Schott,
2006, pp. I-3).
Although money laundering often involves a complex series of transactions that are
usually difcult to separate, the following three stages are commonly used to distinguish:
(1) Placement: The initial stage of the process involves placement of illegally derived
funds into the nancial system, usually through nancial institutions. This can be
accomplished by depositing cash into a bank account. Large amounts of cash are
broken into smaller, less conspicuous amounts and deposited over time in different
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/1368-5201.htm
Data mining
301
Journalof Money Laundering
Control
Vol.20 No. 3, 2017
pp.301-310
©Emerald Publishing Limited
1368-5201
DOI 10.1108/JMLC-09-2015-0041

To continue reading

REQUEST YOUR TRIAL