Anti-money laundering systems: a systematic literature review

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 on a categorization, which demarcates solutions, machine learning, data sources, evaluation methods, implementation tools, sampling techniques and regions of study. Originality/value This SLR could serve as a useful basis for researchers and salient decision-makers, who are seeking to understand the nature and extent of the currently available research into AML systems.

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

“…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.…”

“…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.…”

“…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 as a transnational business phenomenon: a systematic review and future agenda

“…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.…”

Enhancing Transaction Monitoring Controls to Detect Money Laundering Using Machine Learning

“…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].…”