Survey of Machine Learning Approaches of Anti-money Laundering Techniques to Counter Terrorism Finance

Labib, Nevine Makram; Rizka, Mohamed Abo; Shokry, Amr Ehab Muhammed

doi:10.1007/978-981-15-3075-3_5

Cited by 12 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over last decades several papers have been published with different machine learning techniques summarized in many comprehensive literature review papers such as [3,21,24,25], however by looking at the penalties issued by authorities for financial institutions in single year 2019 [11], it is evident that the published methods are either not useful or not used.…”

Section: Discussionmentioning

confidence: 99%

“…A review conducted by [21] has brought out the machine learning algorithms used for identifying the money laundering patterns, detect unusual behavior, identify money laundering groups, and detecting money laundering groups. The identified ML algorithms/techniques are -Rule Based Methods, Decision Trees, Artificial Neural Networks (ANN), Support vector Machines (SVM), Random Forest, Outlier Detection Methods, Social Network Analysis (SNA), Naive Bayes, K-Nearest Neighbor (KNN), Deep Learning, Graph Mining, K-Means Clustering and One Class SVM.…”

Section: A Machine Learningmentioning

confidence: 99%

“…The solutions to detect the money laundering pattern have been evolving from statistical methods , data mining [19,20] and ML [13,21] to DL [22,23]. There are several review papers in literature that demonstrates the application of these methods for detecting suspicious transactions [3,13,20,21,[24][25][26][27][28][29], however lacks the focused review on deep learning techniques or XAI techniques in the same domain.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

et al. 2021

View full text Add to dashboard Cite

Money laundering has been a global issue for decades, which is one of the major threat for economy and society. Government, regulatory and financial institutions are combating it together in their respective capacity, however still billions of dollars in fines by authorities make the headlines in the news. High-speed internet services have enabled financial institutions to deliver better customer experience through multi-channel engagements, which has led to exponential growth in transactions and new avenues for laundering the money for fraudsters. Literature shows the usage of statistical methods, data mining and Machine Learning (ML) techniques for money laundering detection, but limited research on Deep Learning (DL) techniques, primarily due to lack of model interpretability and explainability of the decisions made. Several studies are conducted on application of ML for Anti-Money Laundering (AML), and Explainable Artificial Intelligence (XAI) techniques in general, but lacks the study on usage of DL techniques together with XAI. This paper aims to review the current state-of-the-art literature on DL together with XAI for identifying suspicious money laundering transactions and identify future research areas. Key findings of the review are, researchers have preferred variants of Convolutional Neural Networks, and AutoEncoder; graph deep learning together with natural language processing is emerging as an important technology for AML; XAI use is not seen in AML domain; 51% ML methods used in AML are non-interpretable, 58% studies used sample of old real data; key challenges for researchers are access to recent real transaction data and scarcity of labelled training data; and data being highly imbalanced. Future research directions are, application of XAI techniques to bring-out explainability, graph deep learning using natural language processing (NLP), unsupervised and reinforcement learning to handle lack of labelled data; and joint research programs between research community and industry to benefit from domain knowledge and controlled access to data.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: A Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering–A Critical Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…As banking is the most significant sector affected by money laundering (Raweh et al , 2017), its transaction monitoring ability plays an especially vital role in detecting criminals during the layering stage of the process. According to Labib et al (2020):…”

Section: Literature Reviewmentioning

confidence: 99%

“…AML is essentially a software system designed for this purpose. The aim is to detect suspicious transactions and anomalies in a large withdrawal, a sudden increase in funds, or small patterned transactions, by analysing customer profile data (Labib et al , 2020). In the late 1990s, these statistical techniques used for pattern detection were mostly present in temporal sequence matching and Bayesian models (Alsuwailem and Saudagar, 2020).…”

Section: Literature Reviewmentioning

confidence: 99%

Investigating the determinants of money laundering risk

Ghulam

Szalay

2023

JMLC

View full text Add to dashboard Cite

Purpose With the growing interconnectedness of global markets brought about by globalization and technological innovation, there is a heightened worldwide risk of money laundering, posing a considerable negative impact on economies and social equality. Therefore, the primary purpose of this research is to examine factors that underpin the pervasiveness of money laundering risk. Design/methodology/approach By using a cross-section sample of 84 countries, the study uses ordered logit and multinomial logit regression to test and explain the role of main and varied determinants of money laundering risk covering countries’ economic, social, regulatory and corporate environment. Findings The authors conclude that, overall, the macroeconomic indicators are less relevant in influencing money laundering risk than the other factors adopted from the Basel report. Nonetheless, the volume of exports and the exchange rate were robust in both the ordered and multinomial regression analyses alongside financial secrecy, auditing standards and corporate transparency. While more financial secrecy and a higher volume of exports were found to increase this risk, the other variables showed a negative relationship. The authors further conclude that it is mostly less secrecy, more transparency and better auditing that could gradually transform a high-risk country into medium risk. Practical implications This study recommends the implementation of publicly accessible ownership registries to address the issues around secrecy, transparency and auditing misconducts. Additionally, the general strengthening of laws and policies in these three domains is also necessary alongside the application of current technologies, such as machine learning, for the detection of money laundering. Originality/value The authors believe this study uses advanced econometric techniques rarely used in the literature on money laundering. Separating the impact of economic and social/regulatory is also valuable

show abstract