The financial security management model in second-tier banks

With the growing socio-economic threats associated with the risk of involving second-tier banks in the legalization of illegal income, it is necessary to create an effective financial monitoring system to reduce this risk. Aim of the research is to propose and test a model of financial security management in second-tier banks in Kazakhstan, based on a combination of clustering models and recursive least squares, which allows for three-level processing of incoming information in banks in order to identify hidden data that pose a financial threat to the activities of second-tier banks. The research methodology is based on a combination of APC-III clustering algorithm models and the recursive least squares (RLS) method, with the algorithm slightly modified in accordance with the OECD recommendations. This ap proach made it possible to consider the operations of banks at three levels and, during transitions, identify suspicious transactions that require immediate examination by the bank’s management. Application of the model made it possible to reveal that, on average, about a third of banks’ operations can be classified as suspicious, which means they require careful study. In our case, we selected 200 cases from the original data mixed with 70 suspicious transactions to study the model. As a result of statistical processing of banking operations, 90 operational data were identified, of which 27 turned out to be suspicious, that is, about 30% of verified transactions were found suspicious. As a result of providing this information, the bank was able to identify 19 transactions aimed at money laundering.

financial monitoring, management model, financial security, banking, financial management, risk management

1. Alpysbayev K.S. O natsional’noy sisteme protivodeystviya legalizatsii dokhodov, poluchennykh prestupnym putem (na materialakh Kazakhstana) // Izvestiya SPbGEU. 2017. - №4 (106). - S.11-115.

2. Chernikova L.I., Zayernyuk V.M. Rol’ bankovskogo sektora v bor’be s otmyvaniyem deneg: otechestvennyy i zarubezhnyy opyt // Natsional’nyye interesy: prioritety i bezopasnost’. 2012. №18. - S.46- 54.

3. Karanina E. V., Blednykh O. I. Financial security as a component of the concept of economic security of the state // The Genesis of Genius. 2016. no. 6. Pp. 94-99

4. Averyanova Yu. g. Theoretical aspects of financial security of a commercial Bank // Economic Sciences, 2011, no. 4, Pp. 220-225.

5. Chong, A., Lopez-De-Silanes, F.: Money laundering and its regulation. Economics & Politics. 27(1), 78-123 (2015). doi:10.1111/ecpo.12051

6. Sat, D.M., Krylov, G.O., Bezverbnyi, K.E., Kasatkin, A.B., Kornev, I.A.: Investigation of money laundering methods through cryptocurrency. Journal of Theoretical and Applied Information Technology. 83(2), 244-254.

7. Teichmann, F.M.J.: Twelve methods of money laundering. Journal of Money Laundering Control. 20(2), 130-137 (2017). doi:10.1108/jmlc-05-2016-0018

8. Melnik D.Yu. (2018). Basic elements and main components of a bank economic safety. The Eurasian Scientific Journal, [online] 4 (10). Available at: https://esj.today/PDF/13ECVN418.pdf (in Russian)

9. Serdyuk V.A. New in protection against hacking of corporate systems / V.A. Serdyuk. - M.: Technosphere, 2007. - 360 p.

10. Pramod, V., Li, J., Gao, P.: A framework for preventing money laundering in banks. Information Management & Computer Security. 20(3), 170-183 (2012). doi:10.1108/09685221211247280

11. Gayduk Vladimir Ivanovich, Vorokov Anzor Ladinovich, Gayduk Natal’ya Viktorovna Finansovaya bezopasnost’ kommercheskikh bankov: kriterii i indikatory // Nauchnyy zhurnal KubGAU - Scientific Journal of KubSAU. 2015. №114. URL: https:// cyberleninka.ru/article/n/finansovaya-bezopasnost-kommercheskih-bankov-kriterii-i-indikatory (дата обращения: 28.09.2020).

12. Evseev S.P. A Synergistic approach to assessing the security of banking systems // Information processing systems, 2016, issue 4 (141). - S.90-103.

13. Kozminykh S.I. Mathematical modeling of ensuring complex security of objects of informatization of the credit and financial sphere // Issues of cybersecurity, 2018. -№1 (25) -. - S.54-63.

14. Mukhopadhyay, A., Chatterjee, S., Bagchi, KK et al. Cyber Risk Assessment and Mitigation (CRAM) Framework Using Logit and Probit Models for Cyber Insurance. Inf Syst Front 21, 997-1018 (2019). https://doi.org/10.1007/s10796-017-9808-5

15. Official website of the OECD [Electronic resource]//http://www.oecd-ilibrary.org/

16. Honghong Duan, Jie Jia, Ruifeng Ding Twostage recursive least squares parameter estimation algorithm for output error models// Mathematical and Computer Modelling Volume 55, Issues 3-4, February 2012, Pages 1151-1159.

17. Benesty J., Paleologu C., Gänsler T., Ciochină S. (2011) Recursive Least-Squares Algorithms. In: A Perspective on Stereophonic Acoustic Echo Cancellation. Springer Topics in Signal Processing, vol 4. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22574-1_6

18. Rafal Drezewskia, Jan Sepielaka, Wojciech Filipkowskib, System supporting money laundering detection // Digital Investigation, 2012. - Vol.9(1). - pp. 8-21.//http://dx.doi.ofg/10.1016/j.diin.2012.04.003

19. Shaten P. L. Prevention of money laundering and terrorist financing: a practical guide for banking professionals-Moscow: Alpina publishers, 2011. - 316p.//https://openknowledge.worldbank.org bitstream/ handle/10986/2638/488950PUB00RUS00Box0361504 B0PUBLIC0.pdf?sequence=7&isAllowed=y

20. Bonnie Buchanana, Money laundering-a global obstacle [Electronic source] // Research in International Business and Finance, 2004. - Vol. 18(1). - pp. 115-127. - //http://dx.doi.org/l0.1016/j. ribaf.2004.02.001.

21. Shijia Gao, Dongming Xu, Coneeptual modeling and development of an intelligent agent- assisted decision support system for anti-money laundering // Expert Systems with Applications, 2009. - Vol. 36 (2). - pp. 1493-1504 // http// dx.doi. org/10.1016/j.eswa.2007.11.059.