05 Predicting Money Laundering Using Machine Learning
05 Predicting Money Laundering Using Machine Learning
05 Predicting Money Laundering Using Machine Learning
net/publication/363023223
CITATIONS READS
0 43
1 author:
Mark Lokanan
Royal Roads University
37 PUBLICATIONS 245 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
All content following this page was uploaded by Mark Lokanan on 30 August 2022.
Abstract: This paper aims to build a machine learning and a neural network model to detect the
probability of money laundering in banks. The paper's data came from a simulation of
actual transactions flagged for money laundering in Middle Eastern banks. The main
findings highlight that criminal networks mainly use the integration stage to integrate
money into the financial system. Fraudsters prefer to launder funds in the early hours,
morning followed by the business day's afternoon time intervals. Additionally, the Naïve
Bayes and Random Forest classifiers were identified as the two best-performing
models to predict bank money laundering transactions.
Introduction
As governments around the world have increased their scrutiny of the gaming and real
estate sectors, there has been a shift in money-laundering activities in the financial industry. An
$2 trillion in transactions were flagged by financial institutions between 1999 and 2017 (Yang et
al., 2020). In many of these instances, criminal networks were probing and detecting weaknesses
in the control and anti-money-laundering (AML) frameworks to launder illicit funds and
integrate them into ostensibly legitimate assets (Hutton, 2020). The end goal is the final
integration of the funds into legitimate business activities or investments. To address these
concerns, there have been calls to employ artificial intelligence (AI) to build learning algorithms
1
intelligence will be transformative in that AI techniques can help reduce false positives or type I
1. How does the probability of money laundering vary by personnel and type of activities?
2. Which features are the strongest predictors of money laundering?
Contribution to Practice
In the past decade, banks have dramatically shifted the way they operate. The traditional
model of banking, which places reliance on human expertise to detect instances of money
laundering, is unable to keep up with the rapid pace of change taking place in the world of
finance. Banks must adopt cutting-edge technologies like machine learning (ML) and artificial
neural networks (ANN) to stay competitive and detect financial crimes. ML is a form of AI that
allows computers to learn from data, identify patterns, and make predictions. Banks are already
using this technology to detect fraud, assess risk, personalize customer service, and process and
interpret large amounts of data. ML technology is particularly well-suited for credit scoring and
money laundering detection tasks. In the ever-evolving world of finance, financial institutions
that use ML and ANN will be able to stay ahead of criminal networks and prevent launders from
the past, banks could relatively quickly identify suspicious activity by looking for patterns in
cheque deposits and withdrawals. However, because of the proliferation of internet banking and
other forms of digital payment, it is now far more challenging to monitor unlawful financial
activities. Banks are fighting back using ML and AI to detect and block suspicious transactions
automatically. By analyzing large datasets, ML and AI can help banks identify trends that may
indicate money laundering. These methods, when combined with business intelligence, have the
potential to provide a potent instrument in the fight against money laundering. Computational
2
technology may help with customer due diligence by identifying account holders and signatures,
account numbers, the name of the bank, and the signature on the account.
The current article aims to predict money-laundering activities in the banking industry
using supervised ML classification techniques and a feedforward neural network model. The rest
of this paper is structured according to the following format: Section two provides a critical
overview of AML and the computational intelligence literature. Section three discusses the
methodology and research design. Section four discusses the data cleaning and processing
process. The algorithms used in this paper are also discussed. Section five analyzes and discusses
the findings. Section six provides a conclusion and highlights areas for future research.
activities into clean money that appears to come from a legitimate source. In other words, it
places illegally sourced funds into the standard financial cycle or money circulation process by
disguising them as clean money (Ardizzi et al., 2014; Sobh, 2020). Money laundering involves
processing funds from underground activities like terrorism, cybercrime, drug trafficking,
corruption, tax evasion, and quasi-legal activities such as concealment of income from public
authorities (Habib et al., 2018; Karim et al., 2020; Tiwari et al., 2020). Converting illegitimate
gain into legitimate income disrupts the legal process of money supply and corrupts financial
institutions, which in turn benefits criminal networks (Ardizzi et al., 2014). Moreover, according
to Hendriyetty and Grewal (2017), money laundering leads to an increase in shadow economic
and criminal activities while reducing the tax collections required for the growth of a country (as
cited in Tiwari et al., 2020). Likewise, Drayton (2002) and Dowers and Palmreuther (2003)
stated that money laundering could stymie a nation's economic growth, lead to financial
3
distortion, socioeconomic and monetary instability, higher corruption, and increased
vulnerability to financial institutions (as cited in Habib et al., 2018; Loayza et al., 2019). This
claim can be exemplified by the research done on 91 Italian states in which the total identified
laundered cash from 2005 to 2008 was equivalent to 7% of Italy's GDP, of which three-fourths
of the money was sourced from illegal trafficking activities. The remaining one-fourth was
acquired through extortion (Ardizzi et al., 2014). Likewise, Loayza et al. (2019) highlighted in
their paper that Colombia saw a phase in 2001 and 2002 when the total value of illicit income
was equal to 12% of its GDP and the volume of laundered assets increased from 8% to 14% of
Colombia's total GDP. As a result, illegal activities like as tax evasion, corruption, extortion, and
drug trafficking result in income loss for the government, internal market instability, erosion of
private-sector efforts, volatile currency and interest rates, and political upheaval (Ofoeda et al.,
Money laundering is primarily a three-step process that involves placement, layering, and
integration stages (Sobh, 2020; Tiwari et al., 2020). The first step, known as placement, involves
the introduction of illegal funds into the financial system; the second stage, known as layering,
involves a series of fictitious transactions that mask the true source of the cash (Ardizzi et al.,
2012; Ofoeda et al., 2020). In the third integration stage, illicit money is converted into a
legitimate source of revenue by investing it in real estate, stocks, or businesses (Ardizzi et al.,
2012). According to Loayza et al. (2019), an illicit process can be categorized into two types of
activities: first, the production of illegal goods (such as drugs) that have value in the illicit
market; and second, activities like kidnapping, extortion, robbery, and fraud that redistribute
wealth among the various classes of people (from rich to poor) but do not contribute to the
economy. The illegal money generated through these two types of illicit activities can be
4
laundered through "front companies," gold dealers, currency exchange houses, insurance
companies, shell companies, wire systems, offshore banking, automobile dealerships, casinos,
lawyers, and accountants," among others (McDowell and Novis, 2001, as cited in Ofoeda et al.,
2020, p. 4).
that contribute to or determine the likelihood of money laundering. According to Karim et al.
(2020), the four variables of the fraud diamond theory—rationalization, pressure, capacity, and
the fraud diamond theory, high living standards, greed for power and money, bad habits or
financial need, loopholes in the current system, insecure e-money facilities, loose control of
access to information, poor supervision, wealth distribution, and urgency, as well as a propensity
to commit fraud and use specific skills to carry out laundering activities, represent the pressure,
opportunities, rationalization, and capability legs of the diamond theory, respectively (Lokanan,
2019).
characteristics that should be considered when developing AML legislation and risk-mitigating
AI algorithms. In this context, Reganati and Oliva (2018) have shown that the factors
determining illegal behaviour might differ by geography. In their paper, Reganati and Oliva
(2018) demonstrated, for instance, that a region's education and corruption level influenced the
mafia crime rate and money-laundering activities in northern and central Italy, whereas gambling
and gaming habits heavily contributed to the presence of money-laundering activities in the
southern region of Italy. Similarly, Amara and Khlif (2018) found that the rate of financial crime
5
is strongly correlated with tax evasion and corruption as a nation's primary driver of financial
crimes.
demonstrating that "a) the probability of being caught for money laundering, b) the sentence for
money laundering, c) the probability of being convicted for the predicate crime, and d) the
transaction costs of money laundering are negatively related to the amount of crime" (p. 1) and
that constructing laws and policies based on these factors will aid in reducing crime. In addition
to the four factors of the diamond theory, the issues of corruption, education, organizational
culture, working environment, money lust, the strictness of laws, the strength of the adopted
audit standards, and the gender, age, source of funds, and number of bank accounts held by
account holders are the major determinants of money laundering that determine the likelihood of
This section will address the role of technology in combating money laundering
challenges. Even though several academics have presented numerous anomaly-detection and
money laundering risk (MLR) mitigation models, it stands to reason that the intended outcomes
would be achieved if technological or software solutions were integrated with those models
(Lokanan, 2019). Similarly, various researchers and practitioners have favoured technology to
enhance the efficacy of anomaly detection and risk-mitigation models (Kansal, 2021; Singh and
Best, 2019). These models need intelligent analytics technologies to identify suspicious activity
via pattern recognition. Analytical methods such as link analysis and interactive data
visualization have proven critical in identifying anomalous patterns and transforming them into
6
visual representations for further human examination (Dilla and Raschke, 2015; Singh and Best,
2019).
More specifically, innovative analytics tools can be used to help detect and prevent
money laundering. By analyzing transaction data, these tools can flag patterns that may indicate
criminal activity (Ferwerda, 2009). These transactions include but are not limited to money
laundering using cash transactions, electronic transfers and payments, bank accounts,
investment-related transactions, offshore activities, secure and unsecured lending, and laundering
involving intermediaries. The information detected from these transactions can then be used by
authorized personnel to form the basis of an investigation. In some cases, smart analytics tools
may even provide real-time alerts to authorized persons when suspicious transactions are
detected and allow for quick and effective action to be taken, potentially preventing large sums
of money from being laundered (Singh and Best, 2019). In conclusion, smart analytics tools can
However, analytics is not particularly useful if data, such as financial transactions, are
created rapidly and in a large volume since analysts would find it difficult to make quick and
accurate choices when dealing with such a dynamic quantity of data (Ferwerda, 2009; Singh and
Best, 2019). Moreover, money launderers regularly use system vulnerabilities and current laws
to launder dirty money; hence, the linear and pattern-based analysis will be unsuccessful unless
the system learns from its previous patterns and creates a new algorithm each time something
Another issue to consider is the cost of implementation. The overall cost of implementing
including the type of algorithm used, the implementation's complexity, and the deployment's
7
scale (Ferwerda, 2009). For example, a simple rule-based algorithm could be implemented for a
few hundred dollars, while a more complex machine learning-based algorithm could cost several
thousand dollars. The cost also scales with the deployment size, so a large bank with millions of
customers would incur much higher costs than a small financial institution (Dreewski et al.,
typically a small fraction of the overall budget for compliance and risk management (Dilla and
Raschke, 2015).
Despite these challenges, ML algorithms are popular and in demand because they can
change as they read new data or patterns (Kansal, 2021; Lokanan and Sharma, 2022; Zhang and
Trubey, 2019). For instance, Semmelbeck et al. (2019) used a random forest (RF) classification
algorithm to identify the factors that could be important to detect whether a terrorist group is
engaged in criminal activities or not and found that the temporal change in the organizational
structure of the terrorist group is a red flag for money-laundering activities. Generally, ML
algorithms used for detecting money-laundering activities can be of two types: supervised and
unsupervised ML algorithms (Chen et al., 2018; Lopez-Rojas and Axelsson, 2012). Badal-Valero
et al. (2018) proposed integrating Benford's rule with ML techniques such as logistic regression
(LR), decision trees (DT), neural networks (NN), and random forests (RF) and employing any
They found that Benford’s law in association with NN works best on unbalanced data,
whereas RF and LR perform best with Benford’s law when balancing methods are applied or
when Synthetic Minority Oversampling Technique (SMOTE) is applied to the data. Zhang and
Trubey (2019) have compared the five supervised ML algorithms - DT, RF, support vector
8
machine (SVM), artificial neural network (ANN), and Bayes Logistic Regression (BLR) against
the standard Maximum Likelihood Logistic Regression (MLLR) and found that ANN performs
best as a rare event classification algorithm. In contrast, SVM and RF can also generate
comparable results when amalgamated with sampling methods. However, the challenge with
supervised techniques is that the data must be devoid of biases and mistakes, the events in the
historical data must be precisely characterized, and each input variable must be precisely
recognized; otherwise, suboptimal results will be generated by the models (Zhang and Trubey,
2019).
Further, these suboptimal results can be avoided by using the XGBoost ML algorithm.
Jullum et al. (2020) demonstrate through their paper that XGBoost is useful in fighting
suboptimal results as it considers nonreported alerts, normal alerts, and flagged alerts equally to
develop a detection algorithm that predicts the probability of money laundering based on the
senders’ or receivers’ background information, as well as their previous actions and transaction
history. Other than the use of boosted algorithms, it is recommended to use unsupervised ML
(2017), unsupervised data techniques are more helpful in identifying money-laundering patterns
and can be instrumental in improving the learning capacity of classification methods. For
example, Chao et al. (2019) used data-mining methods to monitor abnormal behaviours in trade-
which will be beneficial to restraining cross-border capital flow and arbitrage for emerging
markets and developing economies. Another way to overcome the drawbacks of supervised
learning is to combine visuals with the deep learning ML algorithm called graph learning or
clustering algorithm (Dreewski et al., 2012; Weber et al., 2018). Indeed, Li et al. (2020)
9
proposed using FlowScope—a multipartite graph and scalable algorithm—to plot the complete
flow of monetary transaction money from source to destination. According to Li et al. (2020),
FlowScope can outperform the state-of-the-art baselines in identifying the fraudulent accounts
Models based on ML and AI are increasingly being used in a variety of financial crime
applications, including money laundering prediction. While rule-based methods have long been
the standard for detecting and preventing money laundering, AI models offer a more
sophisticated approach considering various factors. Studies have shown that ML and AI models
can outperform rule-based methods in several ways, including accuracy, speed, and scalability
(see Ba and Huynh, 2018; Jullum et al., 2020; Singh and Best, 2019). Money laundering models
based on ML and AI are said to have higher predictive accuracy than the traditional rule-based
approach to detection (Chen et al., 2018; Jullum et al., 2020). Other studies showed that ML and
AI models could handle more volumes of data than traditional rule-based systems and could do
so in a fraction of the time (Lokanan, 2019; Salehi et al., 2017; Sarker, 2022). Finally, AI models
are more effective than rule-based methods at detecting previously unknown money laundering
Even though AI is still in its infancy regarding AML compliance, several financial
institutions are already adopting it for transaction monitoring. However, AI is not the only
method currently used to detect suspicious transactions (Singh and Best, 2019; Sobh, 2020).
Banks have long relied on rules-based systems to flag suspicious transactions, and these systems
are continuously being refined and updated (Mathuva et al., 2020). In addition, banks are also
10
patterns of behaviour. Money laundering detection models based on ML and AI are trained on
historical data to look for red flags signs of money laundering, such as sudden changes in
methods, banks can create a more comprehensive approach to detecting and preventing money
laundering.
Although a lot has been done using ML algorithms in the field of fraud detection and
detect laundering activities (Jullum et al., 2020; Lokanan and Sharma, 2022). The lack of
unavailability of quantitative data (Chen et al., 2018; Tiwari et al., 2020; Zhang and Trubey,
Lopez-Rojas and Axelsson (2012) believe that synthetic data, in the absence of real data, can be
used to stimulate the required dataset for ML algorithms; however, the downside of this
approach is that a biased dataset can be generated, depending on how it has been simulated. That
said, synthetic dataset does provide an avenue to build and train algorithms to detect money-
laundering activities. They advise using synthetic data for experimentation and Multi-Agent
Based Simulation (MABS) until alternative mechanisms for developing more realistic user
datasets become accessible. The present paper attempts to fill this gap by using a simulated
11
H1: Ceteris paribus, the likelihood of money-laundering events is an increasing function that
depends on gatekeepers and the timing of the transaction.
Research Methodology
Data Collection
Data for this project came from a simulation of money-laundering activities in Middle
Eastern banks based on a real dataset. The data were simulated using similar features and data
points that mirror actual transfers of the original dataset. The features used for the simulation
were similar to the processes used in actual transactions. Both the production of money
laundering and non-money laundering were considered. Attempts were made to simulate all
aspects of money laundering and non-money laundering transactions and to provide a relatively
complete simulator. The simulation is based on financial institutions' three processes of money-
laundering techniques: placement, layering, and integration. In simulating each process, a rule
was created to represent cash-in transfers and one for transferred-out funds. An important feature
of the stimulated dataset is that it is flexible and produces a dataset with different parameters.
Feature Variables
Type of Transaction
The type of transaction is classified as either cash-in or transfer-out. The type of transaction was
Level of Crime
The level of crime refers to whether the money-laundering activities were committed by the
head of the financial institution or by a colleague working in the same institution. The level of
crime was coded as a categorical variable and then transformed into dummy variables.
Amount of Money
12
The amount of money is a random continuous variable and represents the actual amount of
Date
Date is simply the day, month, and year of the transaction. The date was further reformatted
using the date and time format in Python as categorical variables representing the days of the
Time
The time of the transaction is a continuous measure rounded to the nearest hour.
The type of money laundering was coded to represent the three stages of the laundering process:
placement, layering, or integration. Each of these variables was later transformed into a
categorical variable.
Target Variable
Money Laundering
The target variable was whether money laundering occurred or not. The target variable was
coded to represent 1 when the transaction was classified as money laundering and 0 when it was
classified as non-money laundering. The formula to represent the target variable is shown in
equation 1:
Coding and analysis were conducted using the Python programming language in a
Jupyter notebook. Scikit-learn was the library of choice. Scikit-learn is a popular ML library
13
used to build and analyze ML algorithms. The Keras open-source software library was used to
perform the ANN analysis in the Jupyter notebook. The ML algorithm and ANN model were
evaluated using the accuracy scores. As this is a classification model, the confusion matrix was
employed to identify false positives or type 1 error. The algorithm with the highest predictive
accuracy was selected as the best classifier. A confusion matrix was used to describe the
performance of the best classification algorithm on the test set (or unseen data). A classification
report with the following performance metrics was also employed to evaluate whether the
model using precision, recall, and the F-1 score was also used to assess whether the model was
capturing the money-laundering category and not only the non-money-laundering classification.
The Receiver Operating Characteristic (ROC) evaluation metric was used to plot the trade-off of
the false positive (x-axis) against the true positive (y-axis). The Area Under the Curve (AUC)
classifications. A completed random model will produce an AUC of 0.5, and a perfect model
will have an AUC of 1. In this regard, the higher the AUC, the better the model distinguishes
Data Preprocessing
In the data preprocessing stage, the dataset was checked for missing values. The level of
crime feature is missing in 38% of the observations. As this is a categorical variable, the mode
was used to impute the missing observations. All duplicate values were deleted from the dataset.
The specific and unique values were identified for all the features. In cases where Not a Number
(nan) values were identified, they were replaced with zero. Some features, such as source and
destination ID, were dropped from the dataset. There was no way to determine the location (i.e.,
14
Feature Engineering
In the data preprocessing stage, the columns for some of the variables were changed to
make them more readable. For example, "isfraud" was changed to "moneylaundering" to reflect
whether a money laundering transaction occurred or not. The same was done for another type of
money laundering. The original data was coded from "type1," "type2," and "type3" to reflect
integration. Feature selection was also used to identify the top five features. As this was a large
dataset comprising 2,340 observations, the data was divided into a 60/40 train/test split. A
standard scalar technique was used to normalize the numeric features. The model will not be
able to analyze dates and times as raw data. As such, the date and time data were first converted
into categorical variables for Exploratory Data Analysis (EDA) and then converted back to
numeric data for the ML and ANN algorithms to analyze. I further transformed the time into
three categorical variables reflecting the morning, afternoon, and evening. There were only
eight feature variables. Even though Spearman's rank correlation coefficient independent check
for attributes listed the top five features, all 14 features were employed to build the final model.
The Naive Bayes (NB) theorem is one of the classifiers employed to predict money-laundering
activities in financial institutions. Recall from Lokanan and Liu (2021) that the NB theorem is
based on the probability that the output in class C given that X = x can be estimated by P(y|x)
from P(y), P(x), and P(x|y) and is represented by the following equation:
15
P(y|x) = P(x|y) _ P(y)/P(x)
Where:
• P(y|x) is the posterior probability of the target variable (y) given predictor variables
(x, features).
The NB classifier works well for big datasets that include a large number of features and
operates on the assumption that the input features are independent of one another for
multinomial distributed data. To build the algorithm for this model, GaussianNB was use along
classification models. Despite its name, logistic regression is a linear model use for
classification when the target variable is binary or consists of multinomial indicators. Logistic
regression uses the sigmoid function. The sigmoid function maps the real value to a value
bounded between 0 and 1 (hence the logistic regression is used for classification models). The
parameters employed for the logistic regression algorithm is solver = liblinear. The basic
assumption with logistic regression is that of the linear function 𝛽0+𝛽1𝑋, which is transferred
using the sigmoid function 𝑆(𝑡); then, no matter what values 𝛽0, 𝛽1, 𝛽2 . . . and 𝛽k X take, 𝑦
(target variable) will always have values of 0 and 1 (e.g., fraud and nonfraud; money laundering
or no money laundering, spam or no-spam). Logistic regression models use this equation to
16
𝑃𝑟(𝑌=1|𝑋=𝑥) =𝑒𝛽0+𝛽1𝑋1/ 1+𝑒𝛽0+𝛽1𝑋
Random forest (RF) is an ensemble classification method that is useful because it adds
additional randomness to the data. Unlike the NB algorithm, RF trains many strong decision
trees and combines their predictions through a bagging process. The RF model was trained on
the following parameters: criterion = "entropy," n_estimators = 100, and random_state = 123. A
diagraphic illustration of the RF model is shown in Figure 1 below. As you can see from Figure
1, there are two sets: a training set labelled in blue and a test set (unseen data) labelled in green.
After training the RF model on the training set (blue circles), the model is then evaluated on the
test set (green circles). The scores from the trees of the test set (in this case, two) are then
When using the Gini index to determine the branching off of nodes in the decision trees, the
mathematical formula for the RF algorithm for classification data is represented by the following
equation:
𝐺𝑖𝑛𝑖 = ∑𝑛𝑖−1(𝑝𝑛 )2
Where:
• Pn represents the relative frequency of the binary class, and ,
• n represent the number of classes
17
Tree 1 Tree 2 Tree 3
CatBoast Algorithm
based search engine) and is easy to use. CatBoast is very useful for datasets where a large
number of the features are categorical variables. The CatBoast algorithm is based on gradient
boosting and ML; it works great when data comes from different sources. Hence, it is useful for
this dataset since the data was a concatenation of two sources of data: one that involves the
transition amount, type of laundering, and date and time, and the other that contains the people
(i.e., head or colleague) who were involved in the laundered activities. The parameters of the
GridSearchCV
Based on the performance metric used to evaluate the model, the single algorithm
outlined above will project the performance of the parameters that come with those algorithms.
For these parameters, the only choice is to try all the possible values and then choose the best
one. To further fine-tune the model and enhance the performance metrics, GridSearchCV ("grid
18
search") is used. The grid search approach generates the best candidate from a specified list of
parameters. There are two types of grid search: exhaustive and randomized. The exhaustive grid
search approach optimizes the parameters to be included in the model, whereas the randomized
grid search approach automatically selects the best parameters for the model. In this project, an
exhaustive grid search was employed to select the best parameters for the model. The exhaustive
grid search approach was chosen because all the possible parameters are evaluated, and the best
The ANN method is a generalized model that processes many layers of data to make a
decision. As can be seen in Figure 2 below, ANN is a multilayered layer perceptron (MLP)
approach, where the input features are given values or weights. The MLP method is a deep
learning neural network approach composed of several perceptrons. As can be seen in Figure 2,
the MLP method consists of three layers: the input layer, which receives the signals from the
modes; the output layer, which calculates the weighted average of the single features; and the
output layer, which receives the weighted sum from the output layer to make a decision. In
classification problems, the decision will be based on the percentage or accuracy of the model to
predict the outcome. The input layers are typically the feature variables of the model. The input
layers pick up the signals (coefficients) and pass them on to the hidden layer, where the weighted
average for each feature is calculated and passed on to the output layer, which delivers the
results. ANN is like a black box. It is not supposed to be interpretable in terms of feature
importance; rather, it is a useful algorithm for predictive models and can be analyzed using the
19
X0
W H0
1
X1 Y1
W2
H1
X2
W3 Y0
H2
W4
X3
Analysis of Findings
Univariate Analysis
Table 1 presents the descriptive statistics of the numerical features. It is important to note
that the maximum amount of funds laundered in a single transaction was $7.95 million. There is
also no significant difference between the average amount of funds laundered ($2.51 million)
Amount of Money
Money Laundering
Laundered
Count 2.34E+03 2340
Mean 2.51E+06 0.597863
Std 2.56E+06 0.490434
Min 1.33E+04 0
25% 3.36E+05 0
50% 1.16E+06 1
75% 4.69E+06 1
Max 7.95E+06 1
Table 2 shows the descriptive statistics of the categorical features. As shown in Table 2,
there are five categorical features. This type of laundering represents the stages of money
20
laundering: placement (type 1), layering (type 2), and integration (type 3). A closer look at Table
2 indicates that integration (type 3) was the top method used to launder funds. Note also that
there are more transfer-out than transfer-in transactions. Interestingly, more colleagues (or
Type of
Type of Action Level of Crime Date Time
Laundering
Count 2340 1449 2340 2340 2340
Unique 2 2 151 475 3
Top transfer colleague 6/6/2019 15:30 type3
Freq 1580 919 26 12 1452
Figure 3 shows the most important features for predicting money-laundering activities in
financial institutions. As seen in Figure 2, the hour of the day has the highest positive impact in
make sense because the amount of funds entering and leaving the system is more likely to be
flagged by compliance officers if they are over the allotted amount or if there is any anomaly
with the transaction. Surprisingly enough, the amount of money does not seem to be an
21
0.3500
Importance 0.3000
0.2500
0.2000
0.1500
0.1000
0.0500
0.0000
Features
Continuing from Figure 3, the timing of the laundering activities is significant. As can be
seen in Figure 4, launderers are more likely to launder funds through on-site transactions and
during business hours. Most of the laundered funds occurred in the morning hours, followed by
the afternoon time intervals. Not surprisingly, laundering activities do not occur during the nights
and evenings because these are outside business hours. According to these results, there is a clear
need for a heightened focus on monitoring transactions in the early morning hours of work days.
22
Figure 4: Transaction time
Bivariate Analysis
Figure 5 presents the correlation matrix of the numerical features with money-laundering
activities. There is a moderately positive correlation (0.57) between the head of the bank and
(-0.57) between colleagues and money-laundering transitions. These findings indicate that the
more funds laundered by colleagues, the less likely the money-laundering transactions will be
successful. Note also from Figure 1 that the placement stage of the laundering process is
positively correlated (0.67) with money laundering. Funds that are transferred out have a
negative (-1) correlation with money laundering, which indicates that once the transactions
(cash-in) are placed in the financial system, they are integrated and become part of the criminal
23
Figure 5: Correlation matrix
performance metrics to consider. The present study is based on a binary classification model to
predict money-laundering transactions and is denoted as 1 (for money laundering) and 0 (for no
24
money laundering). The classification of a particular observation can fall within one of several
Accuracy is simply the number of correctly classified observations (TP + TN) divided by the
total number of observations. Precision is how precise or accurate the model predicts the true
class (in this case, money laundering). Recall, or sensitivity is the positive rate of the true class
that has been correctively classified. The F1- measure is simply the harmonious mean of recall
and precision and might be a better measure if there is a need to balance the scores between
precision and recall in an imbalanced dataset (See Lokanan and Sharma, 2022; Kansal, 2021).
Table 3 presents the accuracy score of the algorithms. As noted in this study, there was
not much difference in the respective scores. Quite notably, the NB and RF classifiers were the
two best-performing models, both with 77.46% accuracy. Significantly enough, grid search,
which involved hyperparameter tuning, did not improve the accuracy score of the model. Given
25
that the NB and RF had the highest accuracy rates, it is logical to look further into their
classification scores. As seen in Table 4 below, when compared to the RF model (.87), the NB
(1.00) classification did an excellent job of not labelling an observation as money laundering that
was not money laundering. On the other hand, RF did a better job of capturing more money
It is essential to have a look at the confusion matrix of the NB and RF classifiers in order
to get further knowledge. Figure 6, below, shows a side-by-side comparison of the NB and RF
confusion matrix. There are two possible outcomes from the predicted class: money laundering
and no money laundering. A closer look at Figure 6 shows that the NB classifier shows that the
model correctly predicted money-laundering transactions 39.4% of the time and no-money-
laundering transactions 38% of the time. Together, those numbers represent 77.4% classification
accuracy. On the other hand, the RF model correctly predicted money-laundering transactions
26
32.9% of the time and no-money-laundering transactions 43.8% of the time. Taken together,
those numbers represent 76.7% classification accuracy. The presence of money laundering was
present 38% of the time and absented 62% of the time. Conversely, the RF classifier predicted
of the time. Interestingly enough, the false positive or Type 1 error, where the models predicted
no money laundering, but money laundering occurred, was 0% for the NB model compared to
6.5% for the RF model. When one considers the large percentage of true positives and negatives
for both models, they are fairly good classifiers to predict money-laundering transactions.
The ANN model performed slightly better than the classical ML models. The accuracy of
the training and test sets is 78% and 80%, respectively. These results indicate that the ANN
27
model did an excellent job predicting money-laundering transactions. More importantly, the
model did not suffer from underfitting or overfitting the data. The ANN model is, therefore, very
good at generalizing from the test set. The precision score is 87%, and the recall score is 72%;
these findings indicate that the model is very good at predicting money-laundering transactions
and correctly identifying individuals who are laundering money through the financial system.
Figure 7 presents the results for the ROC curve for both the training and test sets. The AUC for
the test set is 78% (rounded), which indicates that the model performance was decent when
Conclusion
Money laundering is all about converting dirty money into clean funds. The involvement
28
algorithms employed in this paper perform reasonably well in identifying and labelling money-
laundering transactions (see also Jullum et al., 2020; Tiwari et al., 2020; Zhang and Trubey,
2019). At the very least, compliance officers should use the findings presented here to scrutinize
the features related to the laundering of funds. Features such as the time of the day and the
amounts of money coming in and transferred out should be comprehensively monitored and
scrutinized with regulatory technology. Other factors that should be monitored closely are
international payments, sudden changes in the source of income, considerable anomalies in the
amounts of money transfers, and any other suspicious activity that should be immediately
Financial institutions should use the findings from this paper to maintain lower money-
laundering risks and conduct due-diligence background checks on the source of the cash-in funds
and the destination of the transfer-out funds (Ba and Huynh, 2018; Tran and Nguyen, 2017). The
machine-learning and ANN algorithms can be used to inform and continuously update money-
laundering risks for each customer and incorporate new features such as salary, occupation, and
source of income (Tran and Nguyen, 2017). Any abrupt changes in a customer’s profile will act
as red flags that would be eligible for scrutiny. Indeed, there should be proper training of bank
employees and frontline workers to ensure that they are capable of identifying hot spots
identified by the algorithms (Isa et al., 2015; Usman Kemal, 2014), while not ignoring their
identify and report unusual activities (Usman Kemal, 2014). The findings presented in this paper
support the claim that there is scope to develop ML and AI models to detect illicit activities in
financial institutions.
29
Financial institutions should use the findings from this paper to maintain lower money-
laundering risks and conduct due-diligence background checks on the source of the cash-in funds
and the destination of the transfer-out funds (Ba and Huynh, 2018; Tran and Nguyen, 2017). The
ML and ANN algorithms can be used to inform and continuously update money-laundering risks
for each customer and incorporate new features such as salary, occupation, and source of income
into the models (Tran and Nguyen, 2017). Any abrupt changes in a customer’s profile will act as
red flags that would be eligible for scrutiny. Indeed, there should be proper training of bank
employees and frontline workers to ensure that they are capable of identifying hot spots
identified by the algorithms (Isa et al., 2015; Usman Kemal, 2014), while not ignoring their
identify and report unusual activities (Usman Kemal, 2014). The findings presented in this paper
support the claim that there is scope to develop ML and AI models to detect illicit activities in
financial institutions.
References
Al-Suwaidi, N. A., & Nobanee, H. (2020). Anti-money laundering and anti-terrorism financing:
A survey of the existing literature and a future research agenda. Journal of Money
Laundering Control, ahead-of-print(ahead-of-print). https://doi.org/10.1108/JMLC-03-
2020-0029
Amara, I., & Khlif, H. (2018). Financial crime, corruption and tax evasion: A cross-country
investigation. Journal of Money Laundering Control, 21(4), 545–554.
https://doi.org/10.1108/JMLC-10-2017-0059
30
Amara, I., Khlif, H., & El Ammari, A. (2020). Strength of auditing and reporting standards,
corruption and money laundering: A cross-country investigation. Managerial Auditing
Journal, 35(9), 1243–1259. https://doi.org/10.1108/MAJ-10-2018-2026
Ardizzi, G., De Franceschis, P., & Giammatteo, M. (2018). Cash payment anomalies and money
laundering: An econometric analysis of Italian municipalities. International Review of
Law and Economics, 56, 105–121. https://doi.org/10.1016/j.irle.2018.08.001
Ardizzi, G., Petraglia, C., Piacenza, M., Schneider, F., & Turati, G. (2012). Estimating Money
Laundering through a “Cash Deposit Demand” approach. 1–27.
Ardizzi, G., Petraglia, C., Piacenza, M., Schneider, F., & Turati, G. (2014). Money Laundering
as a crime in the financial Sector: A new approach to quantitative assessment, with an
application to Italy. Journal of Money, Credit and Banking, 46(8), 1555–1590.
Arnone, M., & Borlini, L. (2010). International anti‐money laundering programs: Empirical
assessment and issues in criminal regulation. Journal of Money Laundering Control,
13(3), 226–271. https://doi.org/10.1108/13685201011057136
Ba, H., & Huynh, T. (2018). Money laundering risk from emerging markets: The case of
Vietnam. Journal of Money Laundering Control, 21(3), 385–401.
https://doi.org/10.1108/JMLC-09-2017-0050
Badal-Valero, E., Alvarez-Jareño, J. A., & Pavía, J. M. (2018). Combining Benford’s Law and
machine learning to detect money laundering. An actual Spanish court case. Forensic
Science International, 282, 24–34. https://doi.org/10.1016/j.forsciint.2017.11.008
Canhoto, A. I. (2020). Leveraging machine learning in the global fight against money laundering
and terrorism financing: An affordances perspective. Journal of Business Research, 1–12.
https://doi.org/10.1016/j.jbusres.2020.10.012
Chao, X., Kou, G., Peng, Y., & Alsaadi, F. E. (2019). Behavior monitoring methods for trade-
based money laundering integrating macro and micro prudential regulation: A case from
China. Technological and Economic Development of Economy, 25(6), 1081–1096.
https://doi.org/10.3846/tede.2019.9383
Chen, Z., Van Khoa, L. D., Teoh, E. N., Nazir, A., Karuppiah, E. K., & Lam, K. S. (2018).
Machine learning techniques for anti-money laundering (AML) solutions in suspicious
transaction detection: A review. Knowledge and Information Systems, 57(2), 245–285.
https://doi.org/10.1007/s10115-017-1144-z
31
Chong, A., & Lopez‐De‐Silanes, F. (2015). Money Laundering and its regulation. Economics &
Politics, 27(1), 78–123. https://doi.org/10.1111/ecpo.12051
Dilla, W. N., & Raschke, R. L. (2015). Data visualization for fraud detection: Practice
implications and a call for future research. International Journal of Accounting
Information Systems, 16, 1–22. https://doi.org/10.1016/j.accinf.2015.01.001
Dowers, K., & Palmreuther, S. (2003). Developing an international consensus to combat money
laundering and terrorism financing. Infrastructure and Financial Markets Review, 1, 1–7.
Drayton, F.R. (2002). Dirty money, tax and banking: recent developments concerning mutual
legal assistance and money laundering in the Caribbean Region and the region’s
responses. Journal of Money Laundering Control, 5 (4), 338–344. doi: 10.1108/eb027316
Dreżewski, R., Sepielak, J., & Filipkowski, W. (2012). System supporting money laundering
detection. Digital Investigation, 9(1), 8–21. https://doi.org/10.1016/j.diin.2012.04.003
Dreżewski, R., Dziuban, G., Hernik, Ł., & Pączek, M. (2015, October). Comparison of data
mining techniques for Money Laundering Detection System. In 2015 International
Conference on Science in Information Technology (ICSITech) (pp. 5-10). IEEE.
Ferwerda, J. (2009). The Economics of crime and Money Laundering: Does Anti-Money
Laundering policy reduce crime. Review of Law and Economics, 5, 903.
Ferwerda, J., Kattenberg, M., Chang, H.-H., Unger, B., Groot, L., & Bikker, JacobA. (2013).
Gravity models of trade-based money laundering. Applied Economics, 45(22), 3170–
3182. https://doi.org/10.1080/00036846.2012.699190
Ferwerda, J., van Saase, A., Unger, B., & Getzner, M. (2020). Estimating money laundering
flows with a gravity model-based simulation. Scientific Reports, 10(1), 18552.
https://doi.org/10.1038/s41598-020-75653-x
Habib, A., Hasan, M. M., & Al-Hadi, A. (2018). Money laundering and audit fees. Accounting
and Business Research, 48(4), 427–459. https://doi.org/10.1080/00014788.2017.1392842
Hendriyetty, N., & Grewal, B.S. (2017). Macroeconomics of money laundering: effects and
measurements, Journal of Financial Crime, 24(1), 1, pp. 65-81.
https://doi.org/10.1108/JFC-01-2016-0004
32
Hutton, L. (2020). Why are banks still so vulnerable to money laundering? Finance Digest.
Available at: https://www.financedigest.com/why-are-banks-still-so-vulnerable-to-
money-laundering.html
Isa, Y. M., Sanusi, Z. M., Haniff, M. N., & Barnes, P. A. (2015). Money Laundering risk: From
the bankers’ and regulators perspectives. Procedia Economics and Finance, 28, 7–13.
https://doi.org/10.1016/S2212-5671(15)01075-8
Jullum, M., Løland, A., Huseby, R. B., Ånonsen, G., & Lorentzen, J. (2020). Detecting money
laundering transactions with machine learning. Journal of Money Laundering Control,
23(1), 173–186. https://doi.org/10.1108/JMLC-07-2019-0055
Kansal, A. (2021). Fake News Detection Using Pos Tagging and Machine Learning. Journal of
Applied Security Research, 1-16, https://doi.org/10.1080/19361610.2021.1963605
Karim, A., Mohamed, N., Ahmad, M. A., & Prabowo, H. (2020). Money Laundering in
Indonesia bankers: Compliance, practice, and impact. Proceedings of the Proceedings of
The First International Conference on Financial Forensics and Fraud, ICFF, 13-14
August 2019, Bali, Indonesia. Proceedings of The First International Conference on
Financial Forensics and Fraud, ICFF, 13-14 August 2019, Bali, Indonesia, Bali,
Indonesia. https://doi.org/10.4108/eai.13-8-2019.2294249
Li, X., Liu, S., Li, Z., Han, X., Shi, C., Hooi, B., Huang, H., & Cheng, X. (2020). FlowScope:
Spotting Money Laundering based on graphs. Proceedings of the AAAI Conference on
Artificial Intelligence, 34(04), 4731–4738. https://doi.org/10.1609/aaai.v34i04.5906
Loayza, N., Villa, E., & Misas, M. (2019). Illicit activity and money laundering from an
economic growth perspective: A model and an application to Colombia. Journal of
Economic Behavior & Organization, 159, 442–487.
https://doi.org/10.1016/j.jebo.2017.10.002
Lokanan, M.E. (2019). Data Mining for Statistical Analysis of Money Laundering Transactions.
Journal of Money Laundering Control. https://doi.org/10.1108/JMLC-03-2019-0024
Lokanan M, & Liu S. (2021). Predicting Fraud Victimization Using Classical Machine Learning.
Entropy. 23(3):300. https://doi.org/10.3390/e23030300
Lokanan, M. E., & Sharma, K. (2022). Fraud prediction using machine learning: The case of
investment advisors in Canada. Machine Learning with Applications, 8, 100269,
https://doi.org/10.1016/j.mlwa.2022.100269
33
Lopez-Rojas, E. A., & Axelsson, S. (2012). Money Laundering detection using synthetic data.
The 27th Annual Workshop of the Swedish Artificial Intelligence Society (SAIS), 9.
https://www.diva-portal.org/smash/get/diva2:834701/FULLTEXT01.pdf
Mathuva, D., Kiragu, S., & Barako, D. (2020). The determinants of corporate disclosures of anti-
money laundering initiatives by Kenyan commercial banks. Journal of Money
Laundering Control, 23(3), 609–635. https://doi.org/10.1108/JMLC-01-2020-0001
McCarthy, K. J., van Santen, P., & Fiedler, I. (2015). Modeling the money launderer:
Microtheoretical arguments on anti-money laundering policy. International Review of
Law and Economics, 43, 148–155. https://doi.org/10.1016/j.irle.2014.04.006
Mekpor, E. S., Aboagye, A., & Welbeck, J. (2018). The determinants of anti-money laundering
compliance among the Financial Action Task Force (FATF) member states. Journal of
Financial Regulation and Compliance, 26(3), 442–459. https://doi.org/10.1108/JFRC-11-
2017-0103
Ofoeda, I., Agbloyor, E. K., Abor, J. Y., & Osei, K. A. (2020). Anti-money laundering
regulations and financial sector development. International Journal of Finance &
Economics, 1–20. https://doi.org/10.1002/ijfe.2360
Passas, N. (2003). Informal value transfer systems, terrorism and money laundering (No.
208301; p. 137). Northeastern University.
https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.134.8850&rep=rep1&type=pd
f
Ravenda, D., Valencia-Silva, M. M., Argiles-Bosch, J. M., & García-Blandón, J. (2019). Money
laundering through the strategic management of accounting transactions. Critical
Perspectives on Accounting, 60, 65–85. https://doi.org/10.1016/j.cpa.2018.08.003
Reganati, F., & Oliva, M. (2018). Determinants of money laundering: Evidence from Italian
regions. Journal of Money Laundering Control, 21(3), 402–413.
https://doi.org/10.1108/JMLC-09-2017-0052
Salehi, A., Ghazanfari, M., & Fathian, M. (2017). Data Mining Techniques for Anti Money
Laundering. International Journal of Applied Engineering Research, 12(20), 10084–
10094.
34
Sarker, I. H. (2022). Ai-based modeling: Techniques, applications and research issues towards
automation, intelligent and smart systems. SN Computer Science, 3(2), 1-20.
Semmelbeck, J., Besaw, C., & Link to external site, this link will open in a new window. (2019).
Exploring the determinants of Crime-Terror cooperation using Machine Learning.
Journal of Quantitative Criminology, 1–32.
http://dx.doi.org.ezproxy.royalroads.ca/10.1007/s10940-019-09421-0
Singh, K., & Best, P. (2019). Anti-Money Laundering: Using data visualization to identify
suspicious activity. International Journal of Accounting Information Systems,
34(100418), 1–18. https://doi.org/10.1016/j.accinf.2019.06.001
Sobh, T. S. (2020). An Intelligent and Secure Framework for Anti-Money Laundering. Journal
of Applied Security Research, 15(4), 517-546.
Teichmann, F. M. J. (2020). Money-laundering and terrorism-financing compliance – unsolved
issues. Journal of Money Laundering Control, 23(1), 90–95.
https://doi.org/10.1108/JMLC-02-2018-0014
Tiwari, M., Gepp, A., & Kumar, K. (2020). A review of money laundering literature: The state
of research in key areas. Pacific Accounting Review, 32(2), 271–303.
https://doi.org/10.1108/PAR-06-2019-0065
Tran, H. H. B., & Nguyen, B.-H. (2017). Measuring the money laundering risk from individual
customers and its dterminants—The case of Vietnamese commercial banks. 1–20.
http://veam.org/wp-content/uploads/2017/12/76.-Huynh-Ha-Bao-Tran.pdf
Usman Kemal, M. (2014). Anti-money laundering regulations and its effectiveness. Journal of
Money Laundering Control, 17(4), 416–427. https://doi.org/10.1108/JMLC-06-2013-
0022
Weber, M., Chen, J., Suzumura, T., Pareja, A., Ma, T., Kanezashi, H., Kaler, T., Leiserson, C.
E., & Schardl, T. B. (2018). Scalable graph learning for Anti-Money Laundering: A first
look. ArXiv:1812.00076 [Cs]. http://arxiv.org/abs/1812.00076
Yang, Y., Surane, J., & Onaran, Y. (2020). Banks moved US$2 trillion amid laundering orders,
ICIJ says. BNN Bloomberg. Available at:
https://www.emerald.com/insight/content/doi/10.1108/JMLC-07-2019-0055/full/html
35
Zdanowicz, J. (2009). Trade-Based Money Laundering and Terrorist Financing. Review of Law
& Economics, 5(2), 856–878. https://doi.org/10.2202/1555-5879.1419
Zhang, Y., & Trubey, P. (2019). Machine Learning and sampling scheme: An empirical study of
Money Laundering detection. Computational Economics, 54(3), 1043–1063.
https://doi.org/10.1007/s10614-018-9864-z
36