A Hybrid Approach to Risk Assessment of Suspicious Transactions in Payment Systems
Received: 10 Oct 2026 Revised: 20 Oct 2026 Accepted: 10 Nov 2026
Published: 2026, vol. 30, issue 4, pp. 401–404
Abstract
A hybrid transaction-monitoring approach combines logistic regression with expert rules. On a sample of 300,000 PaySim transactions, test recall increased from 75.32% to 96.10%, while precision decreased from 84.06% to 19.73%; the alert rate was about 0.63%. Features, rules, and threshold selection are specified. Future work introduces behavioral features and trainable score aggregation.
Keywords: machine learning, fraud detection, payment systems, expert rules, behavioral analysis, risk assessment.
BibTeX
@article{IS-Radchenko-Mubarakov2026,
author = {Radchenko, Sergey Andreevich and Mubarakov, Bulat Gazinurovich},
title = {{A Hybrid Approach to Risk Assessment of Suspicious Transactions in Payment Systems}},
journal = {Intelligent Systems. Theory and Applications},
year = {2026},
volume = {30},
number = {4},
pages = {401--404},
}
AMSBIB
\Bibitem{IS-Radchenko-Mubarakov2026}
\by S.\,A.~Radchenko, B.\,G.~Mubarakov
\paper A Hybrid Approach to Risk Assessment of Suspicious Transactions in Payment Systems
\jour Intelligent Systems. Theory and Applications
\yr 2026
\vol 30
\issue 4
\pages 401--404
\lang In Russian
RU