Search results

The purpose of this paper is to develop, describe and validate a machine learning model for prioritising which financial transactions should be manually investigated for potential money laundering. The model is applied to a large data set from Norway’s largest bank, DNB.

A supervised machine learning model is trained by using three types of historic data: “normal” legal transactions; those flagged as suspicious by the bank’s internal alert system; and potential money laundering cases reported to the authorities. The model is trained to predict the probability that a new transaction should be reported, using information such as background information about the sender/receiver, their earlier behaviour and their transaction history.

The paper demonstrates that the common approach of not using non-reported alerts (i.e. transactions that are investigated but not reported) in the training of the model can lead to sub-optimal results. The same applies to the use of normal (un-investigated) transactions. Our developed method outperforms the bank’s current approach in terms of a fair measure of performance.

This research study is one of very few published anti-money laundering (AML) models for suspicious transactions that have been applied to a realistically sized data set. The paper also presents a new performance measure specifically tailored to compare the proposed method to the bank’s existing AML system.

The purpose of this study is to provide a bibliometric analysis of the Journal of Money Laundering and Control (JMLC) from 2010 to 2021 and map its way forward.

A range of bibliometric techniques have been used to analyse the performance of JMLC from Volume 14 (Issue 1) to Volume 24 (Issue 4). The Scopus database has been used to analyse the documents of JMLC. A total of 294 documents are reviewed. The bibliographic data has been analysed using the software VOS viewer and R-studio (Biblioshine) to assess the trend of publications, word growth, keyword co-occurrence, citation analysis, most prolific authors and authors’ impact.

JMLC’s academic contributions, influence and impact have grown progressively. The thematic structure of the journal has evolved into six bibliographic clusters, noted as prevention of corruption due to money laundering; compliance and regulation of money laundering; customer due diligence; role of Financial Action Task Force (FATF) in the financial system of developing countries; control of terrorism and terrorist financing; and role of money laundering in the proceeds of crime.

The constraint of this endeavour largely arises from its selection of bibliographic data being confined to Scopus.

The results of the study would help the current and future authors to understand the emerging themes in the field of money laundering and control. They are also going to help the editors of the journals of this domain to understand the emerging themes and how the published documents are going to contribute the society, throwing light on the controlling and compliance part of money laundering. Future research directions are provided in tackling the problem of money laundering, corruption, terrorism, crime, etc. with the help of financial intelligence, strong FATF all around the world, machine learning, Bitcoin exchange management and global knowledge management.

To the best of the authors’ knowledge, this is the first objective assessment of the journal. Thus, the results of the study are useful to past and prospective authors, editorial board members, editors, readers and reviewers to gain a one-stop understanding of anti-money laundering actions through the contributions of JMLC.