Architecture of Transaction Monitoring System of Central Banks

DOI

10.2991/aime-17.2017.106How to use a DOI?

Keywords

payment system; information security monitoring; probabilistic logic models; information security risks; initiating events

Abstract

The detection of fraud payments is one of the primary problems for cyber-security of payment services. Among all services, the exclusive ones are the payment systems of central banks regarding their critical role for financial systems, sheer volume and number of transactions and increased attention from perpetrators. One of the main mechanisms providing detection of fraud operations within interbank netting and settlement payments is a transaction monitoring system. These systems including their complexity and use-case specifics can be represented via probabilistic logic models, considered in this paper. The complete transaction monitoring system comprises several distinct algorithmic modules, which perform tiered checks for conducted payments. To increase adaptability to new types of fraud, the system architecture includes a module of model correction that allows one to detect new threat patterns and to adjust appropriate response while keeping false-positive alerts at low level.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Maxim Repin
AU  - Oleg Mikhalsky
AU  - Ekaterina Pshehotskaya
PY  - 2017/07
DA  - 2017/07
TI  - Architecture of Transaction Monitoring System of Central Banks
BT  - Proceedings of the International Conference "Actual Issues of Mechanical Engineering" 2017 (AIME 2017)
PB  - Atlantis Press
SP  - 654
EP  - 658
SN  - 2352-5401
UR  - https://doi.org/10.2991/aime-17.2017.106
DO  - 10.2991/aime-17.2017.106
ID  - Repin2017/07
ER  -