Abstract:Purpose
This paper aims to understand and document the state of the art in the anti-money laundering (AML) systems literature.
Design/methodology/approach
A systematic literature review (SLR) is performed using the Saudi Digital Library. The outputs published as conference proceedings, workshop proceedings, journal articles and books were all considered. The final sample size after omitting out-of-scope selections was 27 documents, which mainly span from 2015 to 2020.
Findings
The sample is discussed based… Show more
“…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 literature review conducted by [24] focuses on the papers published between 2015 to 2020 to understand the state-of-the-art in AML systems, presents the results using the following categoriessupervised learning, unsupervised learning, data sources, evaluation methods, implementation tools, sampling techniques and regions of study. The key findings by [24] are -Decision Tree, Radom Forest and SVM are most frequently used algorithms in AML system from supervised category, neural networks is mostly used in unsupervised category; Accuracy, Area Under the Curve (AUC) and precision are used for model evaluation; most of the data used for research was customer and transaction data from banks however there are many other methods for laundering the money such as restaurants, hotels and law offices, which are not researched enough.…”
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.…”
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.
“…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 literature review conducted by [24] focuses on the papers published between 2015 to 2020 to understand the state-of-the-art in AML systems, presents the results using the following categoriessupervised learning, unsupervised learning, data sources, evaluation methods, implementation tools, sampling techniques and regions of study. The key findings by [24] are -Decision Tree, Radom Forest and SVM are most frequently used algorithms in AML system from supervised category, neural networks is mostly used in unsupervised category; Accuracy, Area Under the Curve (AUC) and precision are used for model evaluation; most of the data used for research was customer and transaction data from banks however there are many other methods for laundering the money such as restaurants, hotels and law offices, which are not researched enough.…”
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.…”
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.
“…Mostly, the data sources for past reviews were policy documents and reports related to money laundering. Moreover, past reviews tended to focus on the role of machine learning and artificial intelligence in mitigating money laundering (Alsuwailem and Saudagar, 2020; Chen et al , 2018; Han et al , 2020), bibliometric characteristics of publications (Mei et al , 2014) and the role of nonprofit organizations (Omar et al , 2014) or shell companies (Tiwari et al , 2020) in laundering money. Alternatively, we distinguish our study by emphasizing the money laundering aspects relevant to IB.…”
Purpose
Money laundering continues to emerge as a transnational phenomenon that has harmful consequences for the global economy and society. Despite the theoretical and practical magnitude of money laundering, international business (IB) research on the topic is scarce and scattered across multiple disciplines. Accordingly, this study aims to advance an integrated understanding of money laundering from the IB perspective.
Design/methodology/approach
The authors conduct a systematic review of relevant literature and qualitatively analyze the content of 57 studies published on the topic during the past two decades.
Findings
The authors identify five streams (5Cs) of research on money laundering in the IB context: the concept, characteristics, causes, consequences and controls. The analysis further indicates six theoretical approaches used in the past research. Notably, normative standards and business and economics theories are dominant in the extant research.
Research limitations/implications
The authors review the literature on an under-researched but practically significant phenomenon and found potential for advancing its theoretical foundations. Hence, the authors propose a 5Cs framework and a future agenda for research and practice by introducing 21 future research questions and two plausible theories to help study the phenomenon more effectively in the future.
Practical implications
In practical terms, the study extends the understanding of the money laundering phenomenon and subsequently helps mitigating the problem of money laundering in the IB environment, along with its harmful economic and societal impacts.
Originality/value
The authors offer an integrative view on money laundering in the IB context. Additionally, the authors emphasize wider discussions on money laundering as a form of mega-corruption.
“…Many papers over the last demi-decade have applied various machine learning techniques to improve money laundering detection. Review papers such as [19], [8], [6], [20] have summarized the general AML methods in the literature, but it's apparent that the methods are untrusted by financial institutions and consequently unused as fines are increasing. In 2018 fines totaled $4 billion, increasing to $8 billion in 2019, and in the first half of 2020 was $6 billion [21].…”
Section: Key Shortcomings and Future Research Directions For Transact...mentioning
Money laundering has become a great economic problem with huge consequences on society and financial institutions in the last decade. Current anti-money laundering (AML) procedures within the industry are either inefficient due to criminals' increasingly sophisticated approaches or technological advancements. This paper provides an extended abstract to identify and analyze the machine learning methods to detect money laundering through transaction monitoring in the literature. Moreover, the paper identifies research gaps and based on the observed limitations, suggests future research directions and areas in need of improvements.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.