Browse
Recent Submissions
Item Forecasting electricity generation from renewable sources in developing countries (on the example of Ukraine)(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Miroshnychenko, Ihor; Мірошниченко, Ігор Вікторович; Мирошниченко, Игорь Викторович; Kravchenko, Тetiana; Кравченко (Лук’янець), Тетяна Володимирівна; Лук’янець, Тетяна Володимирівна; Drobyna, YuliiaElectricity generation forecasting is a common task that helps power generating companies plan capacity, minimize costs, and detect anomaly. Despite its importance, there are serious challenges associated with obtaining reliable and high-quality forecasts, especially when it comes to the newly created renewable electricity market. A practical approach to predicting the generation of electricity from alternative sources in developing countries (on the example of Ukraine) based on the use of classical (ARIMA, TBATS) and modern (Prophet, NNAR) approaches is proposed. The legal framework regulating the process of Ukraine's entry into the pan-European energy market and its functioning was analyzed: the weak points of the legislation on responsibility, the permissible accuracy of weather conditions data, and the lack of data on the monitoring infrastructure are indicated. Among all the proposed alternatives, the Prophet model was the most accurate, since it allows you to simultaneously take into account several seasonalities (hourly, daily, weekly, monthly, and holidays). According to this, for an operational forecast (6 hours) the best model is the one that takes into account hourly seasonality, and for shortterm forecasts (24 and 48 hours) and medium-term forecast (72 hours) the most accurate models are those taking into account hourly, daily, weekly seasonality and weather conditions. The obtained forecasts and model quality indicators approve the feasibility of applying the proposed approach and the constructed models that can be used in a wide range of economic problems.Item Neuromodeling of features of crisis contagion on financial markets between countries with different levels of economic development(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Lukianenko, Dmytro; Лук’яненко, Дмитро Григорович; Лукьяненко, Дмитрий Григорьевич; Strelchenko, InnaThe study examines the problem of modeling the effects of the spread of crises between countries with different levels of economic development. The main focus is on the study of the spread of crisis contagions from the economy of the source country to the economies of the recipient countries. The authors conducted a fundamental analysis of the basic theoretical concepts, causes and mechanisms of crisis in the world economy. The relevant study was carried out in the context of certain types of financial crises. A methodological approach to modeling the processes of crisis contagion through financial and trade transmission channels has been developed and substantiated. In particular, a method of classifying economies according to the level of behavioral similarity of individual indicators of resilience within two years after the end of the latency period is proposed. The practical implementation of the technique in the form of a cyclic algorithm in the MATLAB system is performed. Approbation of the created software is performed on the data of the world financial crisis of 2008-2009. The obtained distribution of world economies and the calculation of statistical characteristics for each cluster made it possible to identify nine scenarios of economic development under the influence of crossborder processes of crisis. The influence of the type of exchange rate regime on the dynamics of the exchange rate during two years after the end of the latent period is analyzed separately. The analysis of the exchange rate in clusters showed that there is a certain relationship between the type of currency regime and the consequences of the crisis in domestic financial markets.Item Fuzzy logic model of usability of websites of higher education institutions in the context of digitalization of educational services(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Kucherova, Hanna; Honcharenko, Yuliia; Ocheretin, Dmytro; Bilska, OlhaThe purpose of the study is to substantiate a fuzzy logic model for the usability of websites of higher education institutions in the context of digitalization of educational services based on the previous results of the stakeholder survey in accordance with the selected criteria: loading speed, convenience, efficiency, relevance, accessibility, interactivity, cross-browser compatibility, lack of forced content, attractive design, satisfaction. The research methodology is based on the results of the previous scoring of personal data and fuzzy logical conclusions of stakeholders regarding the convenience of using the websites of higher education institutions. As a result, a model of fuzzy logical inference was substantiated and implemented in the Fuzzy Logic Toolbox MatLab environment according to the Mamdani algorithm based on 180 constructed rules. As a result of a study of eight institutions of higher education, the degree of usability of their sites was determined and a quantitative assessment of usability was obtained. The scope of application of the modeling results concerns the possibilities of providing a more accurate understanding of the directions for making further management decisions regarding improving the usability of the site in order to provide quality educational services within the boundaries of the existing online interaction of higher education institutions and their stakeholders. In practice, the use of the developed model is an effective tool for ensuring the quality of educational services in the context of active digitalization of the functioning of higher education institutions.Item EU countries clustering for the state of food security using machine learning techniques(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Kobets, Vitalii; Novak, OleksandraThe food security problem has emerged from the growing pressure of demographic problem and global inequality. Overall, the state of food security is optimal in the EU. This was achieved due to effective implementation of regulatory initiatives regarding EU countries food self-sufficiency and intra-EU food market protection. The purpose of the research paper was to cluster EU countries in terms of food security level using advanced mathematical modeling tools. To this end, we selected 5 food security factors (FAO Food production index, Total factor productivity in agriculture, Per capita agricultural expenditure, Consumer prices food, Net trade food index) to which we applied the following cluster analysis algorithms (self-organizing maps, dendrograms, k-means and k-medoids clustering). As a result of the conducted experimental research, it was found that self-organizing maps and dendrograms methods to be better suited for data visualization, whereas k-means and k-medoids give more accurate and detailed solutions. The obtained results gave us an opportunity to define the advantages and disadvantages of the selected clustering methods, as well as to present agripolicy recommendations for different groups of EU countries.Item Time series forecasting of agricultural product prices using Elman and Jordan recurrent neural networks(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Kmytiuk, Tetiana; Majore, GintaMost practical problems of forecasting time series are characterized by a high level of nonlinearity and nonstationarity, noise, the presence of irregular trends, jumps, and anomalous emissions. Under these conditions, statistical and mathematical assumptions limit the possibility of applying classical forecasting methods. The main disadvantage of statistical models is the difficulty of choosing the type of model and selecting its parameters. An alternative to these methods may be methods of computational intelligence, which include artificial neural networks, which can significantly improve the accuracy of time series prediction. A significant advantage of neural networks is that they are able to learn and generalize the accumulated knowledge, highlighting the hidden relationships between input and output data. At the moment, the most time series forecasting solutions based on this toolkit involve the use of feed-forward neural networks (perceptrons, convolutional neural networks, etc.). The article provides an overview of the architecture, principles of operation, and methods of teaching known models of recurrent neural networks. In the study, we built and compared the architectures of Elman and Jordan neural networks for solving the problem of forecasting prices for agricultural products. The corresponding statistical comparisons of the above models are also given. The experimental results show that such approach provides high accuracy in predicting the values from the price of agriculture products.Item Modeling relation between at-the-money local volatility and realized volatility of stocks(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Bondarenko, MaksymIn this work we apply univariate and multivariate linear regressions to model the relation between at-the-money local volatility and realized volatility of stocks on the example of Microsoft shares. Local volatility is extracted from the set of Vanilla option prices on Microsoft stocks by assuming that Microsoft stock price follows Dupire local volatility process. At-the-money local volatility at different maturities is then used in linear regression predictor while realized volatility is a resulting variable. To handle the ill-posed character of Dupire calibration problem we use genetic algorithm of optimization. To obtain two local volatility datasets (regression inputs) two runs of the calibration are executed as we want to reflect the random nature of the genetic algorithm that can give slightly different values of local volatility for different runs. The model validation is performed by predicting out-of-sample realized volatility using local volatility and comparing it to real world values of the realized volatility. The statistical significance of local volatility is measured as a predictor of realized volatility at different maturities in the article. It is concluded that in all models the local volatility at longer maturities proves to be significant predictor of realized volatility (whether we predict realized volatility in a short time interval or in a longer one). Therefore it makes sense to predict the volatility on the market by calibrating local volatility from the options with longer maturities.Item Identifying stock market crashes by fuzzy measures of complexity(ДВНЗ «Київський національний економічний університет імені Вадима Гетьмана», 2021) Bielinskyi, Andrii; Soloviov, Volodymyr; Semerikov, Serhii; Soloviova, ViktoriiaThis study, for the first time, presents the possibility of using fuzzy set theory in combination with information theory and recurrent analysis to construct indicators (indicators-precursors) of crisis phenomena in complex nonlinear systems. In our study, we analyze the 4 most important crisis periods in the history of the stock market – 1929, 1987, 2008 and the COVID-19 pandemic in 2020. In particular, using the sliding window procedure, we analyze how the complexity of the studied crashes changes over time, and how it depends on events such as the global stock market crises. For comparative analysis, we take classical Shannon entropy, approximation and permutation entropy, recurrent diagrams, and their fuzzy alternatives. Each of the fuzzy modifications uses three membership functions: exponential, sigmoidal, and simple linear functions. Empirical results demonstrate the fact that the fuzzification of classical entropy and recurrence approaches opens up prospects for constructing effective and reliable indicators-precursors of critical events in the studied complex systems.