Combating money laundering with machine learning – applicability of supervised-learning algorithms at cryptocurrency exchanges
| DOI | https://doi.org/10.1108/JMLC-09-2021-0106 |
| Published date | 18 November 2021 |
| Date | 18 November 2021 |
| Pages | 766-778 |
| Subject Matter | Accounting & finance,Financial risk/company failure,Financial compliance/regulation,Financial crime |
| Author | Eric Pettersson Ruiz,Jannis Angelis |
Combating money laundering with
machine learning –applicability of
supervised-learning algorithms at
cryptocurrency exchanges
Eric Pettersson Ruiz
CGI, Stockholm, Sweden, and
Jannis Angelis
KTH Royal Institute of Technology, Stockholm, Sweden and
IFN Research Institute of Industrial Economics, Stockholm, Sweden
Abstract
Purpose –This study aims to explorehow to deanonymize cryptocurrency money laundererswith the help
of machine learning (ML). Money is laundered through cryptocurrencies by distributing funds to multiple
accounts and then reexchanging the crypto back. This process of exchanging currencies is done through
cryptocurrency exchanges. Current preventive efforts are outdated, and ML may provide novel ways to
identify illicit currency movements. Hence, this study investigates ML applicability for combatting money
launderingactivities using cryptocurrency.
Design/methodology/approach –Four supervised-learning algorithms were compared using the
BitcoinElliptic Dataset. The methodcovered a quantitative analysisof the algorithmic performance,capturing
differences inthree key evaluation metrics of F1-scores,precision and recall. Two complementaryqualitative
interviewswere performed at cryptocurrencyexchanges to identifyfit and applicabilityof the algorithms.
Findings –The studyresults show that the current implementedML tools for preventingmoney laundering
at cryptocurrencyexchanges are all too slow and needto be optimized for the task. The resultsalso show that
while not one single algorithm is most suitable for detecting transactions related to money-laundering, the
specificapplicability of the decisiontree algorithm is most suitablefor adoption by cryptocurrencyexchanges.
Originality/value –Given the growthof cryptocurrency use, this study exploresthe newly developed field
of algorithmic tools to combat illicit currency movement, in particular in the growing arena of
cryptocurrencies. The study results provide new insights into the applicability of ML as a tool to combat
money launderingusing cryptocurrency exchanges.
Keywords Anti-money laundering, Machine learning, Supervised learning, Algorithms,
Cryptocurrency
Paper type Research paper
1. Introduction
Cryptocurrencies are a financial asset class increasing in use, with traded cryptocurrencies
having a market capitalization of over $3 trilion in 2021 (Ossinger, 2021). They have an
© Eric Pettersson Ruiz and Jannis Angelis. Published by Emerald Publishing Limited. This is
published under the Creative Commons Attribution (CC BY 4.0) licence. Anyone may reproduce,
distribute, translate and create derivative works of this article (for both commercial and non-
commercial purposes), subject to full attribution to the original publication and authors. The full
terms of this licence may be seen at http://creativecommons.org/licences/by/4.0/legalcode
JMLC
25,4
766
Journalof Money Laundering
Control
Vol.25 No. 4, 2022
pp. 766-778
EmeraldPublishing Limited
1368-5201
DOI 10.1108/JMLC-09-2021-0106
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/1368-5201.htm
To continue reading
Request your trial