Vol:.(1234567890)
The Journal of Supercomputing (2024) 80:6264–6284
https://doi.org/10.1007/s11227-023-05708-z
1 3
Automatic suppression of false positive alerts
in anti‑money laundering systems using machine learning
Ahmed N. Bakry
1
· Almohammady S. Alsharkawy
1
· Mohamed S. Farag
1
·
K. R. Raslan
1
Accepted: 1 October 2023 / Published online: 20 October 2023
© The Author(s) 2023
Abstract
Criminal activities generate an estimated $2 trillion in laundered money per year,
highlighting the need for financial institutions to detect and report suspicious activ-
ity to protect their reputation. However, rule-based models commonly used for this
purpose generate a high number of false positives, draining compliance team time,
and increasing investigation costs. However, the application of machine learning in
conjunction with rule-based models presents noteworthy implications, encompass-
ing the potential reduction in false positives and the concomitant risk of machine
learning inadvertently suppressing true positive alerts. This paper proposes a frame-
work called automatic suppression based on XGBoost for anti-money laundering
(ASXAML) to enhance detection by reducing false positives. ASXAML leverages
recursive feature elimination with cross-validation for optimal feature selection.
Subsequently, Optuna is employed to fine-tune hyperparameters for the XGBoost
model. Results indicate that ASXAML achieves an optimal balance between reduc-
ing false positives and avoiding missed money laundering events, with an 86%
F-beta score and only 11% money laundering customers were incorrectly closed out
of 1926 in the test data.
Keywords XGBoost · Optuna · Anti-money laundering · Random forest · Feature
selection · RFECV
* Ahmed N. Bakry
AhmedNagyBakry@gmail.com
Almohammady S. Alsharkawy
alm.alsharkawy@azhar.edu.eg
Mohamed S. Farag
mohamed.s.farag@azhar.edu.eg
K. R. Raslan
kamal_raslan@yahoo.com
1
Department of Mathematics, Faculty of Science, Al-Azhar University, Nasr City, Cairo, Egypt