The article discusses the theoretical foundations of the development of global e-commerce in the processes of globalization. The analysis of the definition of the concept of e-commerce, identified its varieties. The authors investigated the main trends that have developed in the e-commerce market, and provide statistical indicators. In addition, the factors that influence the process of development and distribution of e-commerce in the world are identified. Also highlighted the main problems that do not allow the process of distribution of e-commerce technology to develop the maximum rate.

This paper discusses the problems of short-term forecasting of cryptocurrency time series using a supervised machine learning (ML) approach. For this goal, we applied two of the most powerful ensemble methods including Random Forests (RF) and Stochastic Gradient Boosting Machine (SGBM). As the dataset was collected from daily close prices of three of the most capitalized coins: Bitcoin (BTC), Ethereum (ETH) and Ripple (XRP), and as features we used past price information and technical indicators (moving average). To check the effectiveness of these models we made an out-of-sample forecast for selected time series by using the one step ahead technique. The accuracy rate of the forecasted prices by using RF and GBM were calculated. The results verify the applicability of the ML ensembles approach for the forecasting of cryptocurrency prices. The out of sample accuracy of short-term prediction daily close prices obtained by the SGBM and RF in terms of Mean Absolut Percentage Error (MAPE) for the three most capitalized cryptocurrencies (BTC, ETH, and XRP) were within 0.92-2.61 %.

The dynamic system of control of technological innovations is considered. Its dynamics is described by a vector linear discrete recurrent ratio and influenced by control parameters (controls) and an uncontrollable parameter (vector of risks or obstacles). In this case, the risks in the system of control of technological innovation will imply factors that influence negatively or catastrophically the results the processes, considered in it. To solve the problem on control over technological innovations, we proposed methods based on the construction of predictive sets – reachability regions of the considered dynamic model. These are the sets of all permissible states of a phase vector of the system at an assigned moment, correspondent to the fixed program control and to all permissible vectors of risk. This procedure is accompanied by the minimax-based method for finding a guaranteed result. Its essence is that the value of the worst (maximum) vector of possible risks is the least compared with similar values for the others at minimally guaranteed optimal control. Thus, we minimize the impact of risks in the problem of control of technological innovations, where the risks are uncontrollable parameters. This is implemented based on selection of such optimal control, which would guarantee the obtained result under the influence of any maximal risk from the set of permissible risks. The proposed method enables the development of effective numerical procedures that make it possible to implement computer modeling of dynamics of the studied problem, to form program minimax control over technological innovations and to obtain an optimal guaranteed result. The results reported here could be used for economic-mathematical modeling and for solving other problems on the optimization of data forecasting and control processes under conditions of insufficient information and in the existence of risks. In addition, the developed modeling toolset could form the basis for development of appropriate software-hardware complexes to support making effective control decisions in the innovation activity.

The aim of the article is to develop a procedure for implementing an information and consulting web service for personnel management using modern information technologies. It is proposed to use the object-oriented programming language Java. The work of the program is divided into separate blocks, which can be easily adjusted or even replaced. For this, Spring MVC web technologies are used.The system combines complex algorithms and calculations, while it has high flexibility and extensibility with the ability to implement a high level of protection. Another important aspect of developing a web application is ensuring an appropriate level of security with the ability to configure data transfer through encrypted communication channels using the SSL protocol. To increase the flexibility of the system, it is proposed to implement the relationship with the database as a separate module with the ability to adjust it without affecting the main algorithm.In the information and consulting web-service of the district level, a single program operates - the user interface for access to the client database. At this level, they collect, register and process data from enterprises in the region. This is preceded by the preliminary stages of developing the infological model of the subject area, for example, using the ER-model and data design, with further reflection in the datalogical relational model and its optimization (normalization). For the practical implementation of such a datalogical model, a distributed SQL-Server database management system can be used.

The COVID-19 virus has hit the economy around the world. In Poland, SMEs have the greatest problems with doing business. Border blockades and the quarantine for enterprises in virtually all industries throughout Poland greatly complicated the supply systems and the inventory management process. Up to now, SMEs have acted in group purchasing organizations to improve their competitive position. This form of activity also positively affects their financial security. Therefore, in this paper, the inventory management among this group of companies during the COVID-19 pandemic was analyzed. The purpose of the paper was to show how inventory management strategies changed during the COVID-19 pandemic in SMEs operating in industry GPOs. The analysis was carried out on a group of 88 Polish commercial enterprises operating in purchasing groups. The research period covered the years 2017–2019 and March–June 2020. The research showed a change in inventory management strategy in SMEs during the pandemic time of COVID-19. For the first four months, managers of enterprises tried to pursue a conservative policy and to accumulate stocks in the event of a shortage of supplies. This article also presents the form of security that was applied for SMEs operating in group purchasing organizations (GPOs) to avoid forced downtime caused by the COVID-19 pandemic.