Money laundering control in Mexico. A risk management approach through regression trees (data mining)

Pages427-439
DOIhttps://doi.org/10.1108/JMLC-10-2019-0083
Published date12 March 2020
Date12 March 2020
AuthorJosé Francisco Martínez-Sánchez,Salvador Cruz-García,Francisco Venegas-Martínez
Subject MatterFinancial risk/company failure,Financial compliance/regulation,Financial crime
Money laundering control
in Mexico
A risk management approach through
regression trees (data mining)
José Francisco Martínez-Sánchez and Salvador Cruz-García
Universidad Aut
onoma del Estado de Hidalgo,
Mineral de la Reforma Hidalgo, Mexico, and
Francisco Venegas-Martínez
Instituto Politécnico Nacional, Mexico City, Mexico
Abstract
Purpose This paper is aimed at developing a regression tree model useful to quantify the Money Laundering
(ML) risk associated to a customer prof‌ile and his contracted products (customers inherent risk). ML is a risk to
which different entities are exposed, but mainly the f‌inancial ones because of the nature of their activity, so that they
are legally obliged to have an appropriate methodology to analyze and assess such a risk.
Design/methodology/approach This paper usesthe technique of regression trees to identify, measure
and quantifythe ML customersinherent risk.
Findings After classifying customers as high- or low-risk based on a probability threshold of 0.5, this
study f‌inds that customerswith 56 months or more of seniority are more risky than those withless seniority;
the variables contracted productandcustomer seniorityare statistically signif‌icant;the variables origin,
legal entity and economic activity are not statistically signif‌icant for classifying customers; institution
collection, business productsand individual product are the most risky; and the percentage of effectiveness,
suggestedby the decision tree technique, is around 89.5 per cent.
Practical implications In the daily practice of ML risk management, the two main issues to be
consideredare: 1) the knowledge of the customer, and 2) the detection of his inherent risk elements.
Originality/value Information from the customer portfolio and his transaction prof‌ile is analyzed
through BigDataand data mining.
Keywords Data mining, Money laundering, Regression trees, Risk control methodology
Paper type Research paper
1. Introduction
The Mexican National Banking and Securities Commission (CNBV for its acronym in Spanish)
def‌ines money laundering (ML) as the process whereby the origin of the funds generated by the
exercise of any illegal activities is concealed (drug traff‌icking, weapons smuggling, corruption,
fraud, tax evasion, human traff‌icking, kidnapping, prostitution, extortion, piracy, tax evasion,
etc.), making these proceeds appear to have originated from legitimate activities.
The process of ML mainlyconsists of three stages:
(1) Placement, this is the physical disposal of cash proceeds derived from illegal
activity. The funds are placed in the legitimate f‌inancial system, for example, by
making bank deposits in cash or by investing in f‌inancial instruments.
JEL classif‌ication C02, C14, G21, D81
Money
laundering
control in
Mexico
427
Journalof Money Laundering
Control
Vol.23 No. 2, 2020
pp. 427-439
© Emerald Publishing Limited
1368-5201
DOI 10.1108/JMLC-10-2019-0083
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/1368-5201.htm

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT