Data on global financial statistics demonstrate that total losses from fraudulent transactions around the world are constantly growing. The issue of payment fraud will be exacerbated by the digitalization of economic relations, in particular the introduction by banks of the concept of "Bank-as-a-Service", which will increase the burden on payment services. The aim of this study is to synthesize effective models for detecting fraud in digital payment systems using automated machine learning and Big Data analysis algorithms. Approaches to expanding the information base to detect fraudulent transactions have been proposed and systematized. The choice of performance metrics for building and comparing models has been substantiated. The use of automatic machine learning algorithms has been proposed to resolve the issue, which makes it possible in a short time to go through a large number of variants of models, their ensembles, and input data sets. As a result, our experiments allowed us to obtain the quality of classification based on the AUC metric at the level of 0.977-0.982. This exceeds the effectiveness of the classifiers developed by traditional methods, even as the time spent on the synthesis of the models is much less and measured in hours. The models' ensemble has made it possible to detect up to 85.7 % of fraudulent transactions in the sample. The accuracy of fraud detection is also high (79-85 %). The results of our study confirm the effectiveness of using automatic machine learning algorithms to synthesize fraud detection models in digital payment systems. In this case, efficiency is manifested not only by the resulting classifiers' quality but also by the reduction in the cost of their development, as well as by the high potential of interpretability. Implementing the study results could enable financial institutions to reduce the financial and temporal costs of developing and updating active systems against payment fraud, as well as improve the effectiveness of monitoring financial transactions

The ongoing changes in the legal regulations for banks to conduct financial monitoring make the research on the risk-oriented approach implementation in the Ukrainian banking sector relevant. The declining share of information bearing the signs of internal financial monitoring in the total amount of information provided by banks highlights the need to further improve the methods used to assess suspicious financial transactions conducted by banks and the risks associated with them, given the effectiveness of their detection and depth of consequences. The article is aimed to improve the risk-oriented approach in the primary financial monitoring by banks through the substantiated elements composing the system of significant risks associated with money laundering and terrorist financing. While substantiating the elements composing the system of significant risks associated with money laundering and terrorist financing, it is crucial to consider the international risk management standards based on the assessment of threats, vulnerability to threats and their consequences for the bank and national security at all levels. Implementing the following steps: threat identification considering the type and jurisdiction of customers and types of financial transactions and channels for their implementation, justification of banks’ vulnerability to middle and high level threats, significant consequences of money laundering and terrorist financing risks allowed presenting in detail the areas of interest for the bank risk management. The research determined financial transactions subject to the recommendation to use high, increased and traditional prudence while identifying and verifying transactions. The proposed banks’ prudence areas built in reliance on the analysis of the legal framework for combating money laundering and terrorist financing, statistics provided by the State Financial Monitoring Service and the NBU allow banking institutions to focus on the risks posed by money laundering and terrorist financing, which have a significant impact on their activities. Further research should focus on forming a mathematical tool for assessing the bank’s risks in the financial monitoring of money laundering and terrorist financing.

У статті удосконалено аналітичний підхід до визначення змінності параметрів ефективності ризик-контролю клієнтів банку залежно від зміни видів порушень банків у сфері фінансового моніторингу, що, на відміну від наявних, враховує обґрунтування розподілу банків згідно з рівнями ризику (низький рівень ризику, середній рівень ризику, високий рівень ризику) з визначення їх кількісного значення, динаміку зміни порушень у сфері фінансового моніторингу, обумовленість залежності видів порушень у сфері фінансового моніторингу та формалізацію зв'язків ризик-контролю клієнтів банку з порушеннями у сфері фінансового моніторингу, що дає змогу виявити утворення ризикових ситуацій на початкових етапах, оцінити вагомість їх негативного впливу, що сприяє вжиттю релевантних превентивних заходів у сфері фінансового моніторингу.

Current legislation requires banks to continuously monitor all financial transactions of their customers – both legal entities and individuals. However, despite penalties, in the form of multimillion fines and written warnings most Ukrainian banks do not meet the requirements of the National Bank of Ukraine for development, approval and implementation of internal documents on financial monitoring. The purpose of the article is to summarize the practical experience of the banks in compliance with the policy of risk control of the bank's clients in the financial monitoring system. The sample of this study is 75 Ukrainian banks. The internal documents of existing Ukrainian banks on issues of internal bank financial monitoring were analyzed. The components of the risk control policy of the bank's clients were selected and the information on the completeness of the risk control policy of the bank's clients in the existing banks of Ukraine was summarized. The completeness of the risk-control policy of the bank's clients is determined at thefollowing stages: grouping of components of the risk-control policy of the bank's clients; clustering of Ukrainian banks according to the level of completeness of the bank's clients risk control policy. The method of cluster analysis identified groups of banks for the level of full risk-control of their clients. The four clusters with certain asymmetric distributions in their banks were identified. According to the results of generalization of practical experience of banks in compliance with the risk control policy of the bank's clients in the financial monitoring system, namely internal documents of existing banks on internal financial monitoring, it was found that some banks did not have actually developed internal policies or rules on compliance with the requirements of risk control legislation in the field of financial monitoring.

No abstract