José Francisco Martínez-Sánchez, Francisco Venegas-Martínez and Gilberto Pérez-Lechuga
This paper aims to develop a money laundering risk management model for multiple-purpose financial institutions (SOFOMES, Spanish acronym for “Sociedades Financieras de Objeto…
Abstract
Purpose
This paper aims to develop a money laundering risk management model for multiple-purpose financial institutions (SOFOMES, Spanish acronym for “Sociedades Financieras de Objeto Múltiple”) based on the best international practices.
Design/methodology/approach
A study of a sample of several SOFOMES is carried out through representative surveys and focus groups to collect information to develop a causal model of risk management under a Bayesian network approach together with a Monte Carlo simulation.
Findings
The probability that SOFOMES has a high incidence to be used as a mean of money laundering is 29.3%, correspondingly with a probability of 33.1% of having medium incidence and 37.4% of low incidence.
Research limitations/implications
Only nine SOFOMES were willing to provide information for this study.
Practical implications
In Mexico, there is a large registry in the Ministry of Finance and the Attorney General’s Office of this type of practices in the SOFOMES sector, impacting tax collection and affecting the growth of the real sector. The proposed model serves to establish several preventive policies that reduce the incidence of this type of crime.
Originality/value
As far as the authors know, there is no other study as this one in Mexico or in the rest of the world.
Details
Keywords
José Francisco Martínez-Sánchez, Salvador Cruz-García and Francisco Venegas-Martínez
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…
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 (customer’s 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 uses the technique of regression trees to identify, measure and quantify the ML customer’s inherent risk.
Findings
After classifying customers as high- or low-risk based on a probability threshold of 0.5, this study finds that customers with 56 months or more of seniority are more risky than those with less seniority; the variables “contracted product” and “customer seniority” are statistically significant; the variables origin, legal entity and economic activity are not statistically significant for classifying customers; institution collection, business products and individual product are the most risky; and the percentage of effectiveness, suggested by 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 considered are: 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 BigData and data mining.