درخت حوزه‌های تخصصی

The object of the research is the economic dynamic of a depressed low-productive economy, as exemplified by the modern Ukrainian economy. With the purpose to analyze the main causes and consequences of such an economy, the characteristic tendencies of its functioning, activation of the processes of reformation and growth, there was developed the dynamic economic model with significant share of consumer import and export of raw materials, with the use of IT technology. The model also takes into account the socio-economic clustering of a society. It is formalized in the space of economic variables, which describes respectively the savings (liquid capital) of the main social groups involved in the economy, the prices of consumer products in the domestic and foreign markets, the price of exported raw materials for the exchange rate.The model is intended for qualitative analysis of the processes occurring in the economy described by it, and for conducting computational experiments on the basis of information technologies in simulation mode with its parameters, which allows to identify the most characteristic features of the object of the research. The results of experimental researches with the model allowed to establish the main periods of economic dynamics represented by the dynamic variables model, its specificity and social consequences for the society, which is characterized by a bimodal distribution of savings. There was investigation the dependence of the mode solution from it parameters which means in practice the dependence of economic dynamics from the change of individual conditions and factors of economic development.The obtained results are important for informational and analytical support of decision making processes in order to bring the being studied economy out of a low-productive state.

In this article, we will examine the financial issues related to multi-period routing and positioning and the related costs, and we will examine the related limitations. These decisions are made about location allocation, inventory and routing in a three-tier supply chain, including suppliers, warehouses and customers. We are looking for new ways to make location and routing decisions simultaneously and efficiently. In order to maximize the search space and achieve optimal results, exploratory and meta-heuristic methods have been used. The meta-heuristic technique is usually used to increase the performance of the hybrid technique. Therefore, this paper provides an overview of meta-heuristic methods and their combination to solve problems. It also examines the advantages and disadvantages of the proposed methods to solve these problems in order to provide more efficient methods.

The purpose of the present study is to use the ensemble learning model to combine the predictions of Random Forest (RF), Long-Short Term Memory (LSTM), and Recurrent Neural Network (RNN) models for the Top and Bottom Prices of Bitcoin. To this aim, in the first stage, Bitcoin's top and bottom prices are predicted using three machine learning models. In the second stage, the outputs of the models are presented as feature variables to the Extreme Gradient Boosting (Xgboost) and Light Gradient Boosting Machine (LightGBM) models to predict the price tops and bottoms. Then, in the third stage, the outputs of the second stage are combined through the voting ensemble classifier pattern to predict the next top and bottom prices. The data of top and bottom Bitcoin prices in the 1-hour time frame from 1/1/2018 to the end of 6/30/2022 are used as target variables and 31 technical analysis indicators as feature variables for the three models in the first stage. 70% of the data is regarded as learning data, and the remaining 30% is considered for the second and third stages. In the second phase, 50% of the data is considered for learning the output of the previous stage and 50% for the test data. Finally, the prediction values are evaluated with real data for the three models and the proposed ensemble learning model. The results reveal the improvement of the performance, precision, and accuracy of the ensemble model compared to weak learning models.