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.

With the daily increase in document flow, as well as the transition to paperless document management around the world, the demand for electronic document management systems is increasing. This significantly requires optimization of these systems in terms of quality document information retrieval and document management. However, research based on statistical methods cannot effectively handle large amounts of data extracted from electronic documents. In this regard, machine learning methods can effectively solve this problem. This paper presents an approach to building a model of an intelligent document management system using machine learning techniques to ensure efficient employee performance in organizations. The authors have solved a number of problems to optimize each of the document management subsystems, resulting in the development of an intelligent document management system model, which can be effectively applied to enterprises, government and corporate institutions. The feasibility and effectiveness of the proposed model of intelligent document management system based on machine learning and multi-agent modeling of information retrieval processes provides maximum reliability and reduced time of work on documents. The obtained results show that with the help of the presented model it is possible to further develop an intelligent document management system that will allow an electronic document to qualitatively go through the whole life cycle of a document, starting from the moment of document registration and finishing with its closing, i.e. execution, which will greatly facilitate the daily work of users with large volumes of documents. At the same time, the paper considers the application of topic modeling methods and algorithms of text analysis based on a multi-agent approach, which can be used to build an intelligent document management system.