Tetiana Kmytiuk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tetiana Kmytiuk has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Andriy Matviychuk
Kyiv National Economic University named after Vadym Hetman, Kyiv, Ukraine
4 shared publications - Andrii Bielinskyi
Kyiv National Economic University Named After Vadym Hetman
3 shared publications - Vladimir N. Soloviev
Kyiv National Economic University Named After Vadym Hetman
3 shared publications - Halyna Velykoivanenko
Kyiv National Economic University Named After Vadym Hetman
2 shared publications - Olena Piskunova
Kyiv National Economic University Named After Vadym Hetman
2 shared publications Svitlana Savina
2 shared publications
Latest Publications
- Open Access
- 27 August 2026
- Published by Khmelnytskyi National University in MODELING THE DEVELOPMENT OF THE ECONOMIC SYSTEMS
- No. 3,p. 372-379
DETERMINING OPTIMAL NEURAL NETWORK PARAMETERS FOR PREDICTING THE SUCCESS OF IT PROJECTS
The growing importance of IT projects in the modern economy necessitates the application of advanced analytical tools for assessing their potential success. This study is devoted to determining the optimal parameters of neural network models for predicting the success of IT projects. The main objective is to improve the quality, reliability, and stability of classification results through the justified selection of neural network architecture and its hyperparameters. The research is based on a dataset of Ukrainian IT projects, which ensures the relative stability of the economic environment and minimizes the impact of structural shifts. A set of key factors influencing project success was identified, including financial indicators, user activity metrics, and digital presence characteristics. The success of a project is represented as a binary variable, allowing the problem to be formalized as a binary classification task. Multilayer perceptron models were used as the primary modeling tool, while radial basis function networks were also tested but demonstrated insufficient performance. A series of computational experiments was conducted to determine the optimal number of neurons in the hidden layer. The results indicate that although models with fewer neurons provide higher average accuracy, models with a larger number of neurons ensure greater stability. Considering both accuracy and variability measures, the optimal configuration was identified as a neural network with 12 hidden neurons. Furthermore, the study investigates the potential of ensemble approaches, which combine several neural network models with different configurations. The findings confirm that ensemble structures improve both predictive accuracy and robustness of classification results. The obtained results contribute to the development of methodological approaches for optimizing neural network parameters in IT project success prediction and can be applied in decision-making processes by investors, venture funds, and project managers.
- 27 August 2026
- Published by Khmelnytskyi National University in MODELING THE DEVELOPMENT OF THE ECONOMIC SYSTEMS
- No. 3,p. 372-379
Open AccessDETERMINING OPTIMAL NEURAL NETWORK PARAMETERS FOR PREDICTING THE SUCCESS OF IT PROJECTS
The growing importance of IT projects in the modern economy necessitates the application of advanced analytical tools for assessing their potential success. This study is devoted to determining the optimal parameters of neural network models for predicting the success of IT projects. The main objective is to improve the quality, reliability, and stability of classification results through the justified selection of neural network architecture and its hyperparameters. The research is based on a dataset of Ukrainian IT projects, which ensures the relative stability of the economic environment and minimizes the impact of structural shifts. A set of key factors influencing project success was identified, including financial indicators, user activity metrics, and digital presence characteristics. The success of a project is represented as a binary variable, allowing the problem to be formalized as a binary classification task. Multilayer perceptron models were used as the primary modeling tool, while radial basis function networks were also tested but demonstrated insufficient performance. A series of computational experiments was conducted to determine the optimal number of neurons in the hidden layer. The results indicate that although models with fewer neurons provide higher average accuracy, models with a larger number of neurons ensure greater stability. Considering both accuracy and variability measures, the optimal configuration was identified as a neural network with 12 hidden neurons. Furthermore, the study investigates the potential of ensemble approaches, which combine several neural network models with different configurations. The findings confirm that ensemble structures improve both predictive accuracy and robustness of classification results. The obtained results contribute to the development of methodological approaches for optimizing neural network parameters in IT project success prediction and can be applied in decision-making processes by investors, venture funds, and project managers.
- Open Access
- 30 April 2026
- Published by Khmelnytskyi National University in MODELING THE DEVELOPMENT OF THE ECONOMIC SYSTEMS
- No. 2,p. 130-137
ECONOMETRIC MODELING OF THE INVESTMENT ATTRACTIVENESS OF IT PROJECTS USING LOGISTIC REGRESSION
The purpose of this study is to develop an econometric toolkit for identifying and quantitatively assessing the factors influencing the probability of attracting external financing for IT projects in the context of the digital economy. The methodological framework is based on econometric modeling techniques, in particular binary logistic regression (logit model), as well as system analysis, statistical data processing methods, and approaches to handling imbalanced datasets (reweighting and undersampling). Model validation was performed using the Wald test, likelihood ratio test, and the Hosmer-Lemeshow goodness-of-fit test. Based on the modeling of a sample of Ukrainian IT projects, key determinants of successful fundraising were identified. The presence of early-stage investors was found to have a decisive impact, significantly increasing the likelihood of obtaining financing. A statistically significant positive effect of project commercial orientation and digital presence was established. Furthermore, a synergistic effect between technological innovation, particularly the use of artificial intelligence, and operational flexibility – manifested in reduced time-to-market – was substantiated. The proposed approach can be applied as a decision-support tool in IT project management, particularly for assessing investment attractiveness, optimizing development strategies, and enhancing the efficiency of commercialization processes for innovative products. The practical significance of the developed models lies in their ability to provide IT managers and venture investors with an analytical toolkit for auditing initiatives at early stages, thereby minimizing the «valley of death» risks and optimizing financial resource allocation. The results contribute to risk reduction at the early stages of the project lifecycle and improve the robustness of managerial decision-making. Future research directions involve the use of recurrent neural networks to forecast the long-term evolutionary trajectories of IT products in a global digital market.
- 30 April 2026
- Published by Khmelnytskyi National University in MODELING THE DEVELOPMENT OF THE ECONOMIC SYSTEMS
- No. 2,p. 130-137
Open AccessECONOMETRIC MODELING OF THE INVESTMENT ATTRACTIVENESS OF IT PROJECTS USING LOGISTIC REGRESSION
The purpose of this study is to develop an econometric toolkit for identifying and quantitatively assessing the factors influencing the probability of attracting external financing for IT projects in the context of the digital economy. The methodological framework is based on econometric modeling techniques, in particular binary logistic regression (logit model), as well as system analysis, statistical data processing methods, and approaches to handling imbalanced datasets (reweighting and undersampling). Model validation was performed using the Wald test, likelihood ratio test, and the Hosmer-Lemeshow goodness-of-fit test. Based on the modeling of a sample of Ukrainian IT projects, key determinants of successful fundraising were identified. The presence of early-stage investors was found to have a decisive impact, significantly increasing the likelihood of obtaining financing. A statistically significant positive effect of project commercial orientation and digital presence was established. Furthermore, a synergistic effect between technological innovation, particularly the use of artificial intelligence, and operational flexibility – manifested in reduced time-to-market – was substantiated. The proposed approach can be applied as a decision-support tool in IT project management, particularly for assessing investment attractiveness, optimizing development strategies, and enhancing the efficiency of commercialization processes for innovative products. The practical significance of the developed models lies in their ability to provide IT managers and venture investors with an analytical toolkit for auditing initiatives at early stages, thereby minimizing the «valley of death» risks and optimizing financial resource allocation. The results contribute to risk reduction at the early stages of the project lifecycle and improve the robustness of managerial decision-making. Future research directions involve the use of recurrent neural networks to forecast the long-term evolutionary trajectories of IT products in a global digital market.
- 12 November 2025
- Published by Springer Nature
- p. 353-369
Early Warning Signs: Evaluating Permutation Entropy Metrics for Stock Market Crashes
- 12 November 2025
- Published by Springer Nature
- p. 353-369
Early Warning Signs: Evaluating Permutation Entropy Metrics for Stock Market Crashes
- 30 June 2025
- Published by Academy of Cognitive and Natural Sciences
- p. 83-96
Capturing Bitcoin Market Dynamics: Assessing Advanced Permutation Entropy Metrics as Early-Warning Indicators
Permutation entropy (PEn) is a widely adopted nonlinear statistical measure for quantifying complexity in time series data. Despite its conceptual clarity and computational efficiency, classical PEn has notable limitations, particularly its disregard for amplitude variations in time series data and the simplistic handling of sequences containing equal-valued observations. Although modified PEn methods exist, their potential as early-warning indicators for cryptocurrency market crashes remains largely unexplored. This paper addresses these limitations by conducting a comparative analysis of classical PEn and three enhanced methods: weighted permutation entropy (WPEn), amplitude-aware permutation entropy (AAPEn), and uniform quantization-based permutation entropy (UPEn). Specifically, these entropy metrics are employed to analyze the Bitcoin market crash from December 2017 to February 2018, utilizing a sliding window approach. Empirical results demonstrate that amplitude-enhanced entropy methods effectively capture nuanced market dynamics and fluctuations, offering more precise and more reliable signals of impending market instability. This study confirms the value of advanced entropy measures in cryptocurrency markets and underscores their potential as robust indicators for detecting and forecasting financial crashes.
- 30 June 2025
- Published by Academy of Cognitive and Natural Sciences
- p. 83-96
Capturing Bitcoin Market Dynamics: Assessing Advanced Permutation Entropy Metrics as Early-Warning Indicators
Permutation entropy (PEn) is a widely adopted nonlinear statistical measure for quantifying complexity in time series data. Despite its conceptual clarity and computational efficiency, classical PEn has notable limitations, particularly its disregard for amplitude variations in time series data and the simplistic handling of sequences containing equal-valued observations. Although modified PEn methods exist, their potential as early-warning indicators for cryptocurrency market crashes remains largely unexplored. This paper addresses these limitations by conducting a comparative analysis of classical PEn and three enhanced methods: weighted permutation entropy (WPEn), amplitude-aware permutation entropy (AAPEn), and uniform quantization-based permutation entropy (UPEn). Specifically, these entropy metrics are employed to analyze the Bitcoin market crash from December 2017 to February 2018, utilizing a sliding window approach. Empirical results demonstrate that amplitude-enhanced entropy methods effectively capture nuanced market dynamics and fluctuations, offering more precise and more reliable signals of impending market instability. This study confirms the value of advanced entropy measures in cryptocurrency markets and underscores their potential as robust indicators for detecting and forecasting financial crashes.
- 2 October 2024
- Published by Springer Nature
- p. 243-256
Modeling and Identifying States of Irreversibility in Energy-Related Markets
- 2 October 2024
- Published by Springer Nature
- p. 243-256
Modeling and Identifying States of Irreversibility in Energy-Related Markets
- Open Access
- 20 September 2024
- Published by Institute of Eastern European Research and Consulting in Agricultural and Resource Economics: International Scientific E-Journal
- Vol. 10 (3) , 5-33
Time series forecasting of price of the agricultural products using data science
Purpose. The purpose of our article is to research and forecast prices for agricultural products using the example of potato prices based on the most effective models using data science techniques. Methodology / approach. Various forecasting models are explored, starting from baseline models like decomposition and exponential smoothing models to more advanced techniques such as ARIMA, SARIMA, as well as deep learning models including neural network. The data is split into training and testing sets, and models are validated using cross-validation techniques and optimised through hyperparameter tuning. Model performance is evaluated using metrics such as MAE, MSE, RMSE, and MAPE. The selected model is then used to generate future price forecasts, with uncertainty quantified through confidence intervals. Results. The study successfully applied advanced data science techniques to forecast potato prices, leveraging a range of effective models. By analysing historical price data and using various forecasting methods, the research identified the most accurate models for predicting future price trends. The results demonstrate that the selected models can provide reliable forecasts. In particular, the results showed that the model could achieve good forecast results when applied to real problems and, thus, can be effectively used for forecasting tasks especially considering seasonality. In addition, it should be noted that the model has a higher prediction accuracy at the time intervals closest to the original data. The obtained results support using both models simultaneously for forecasting, which can compensate for the shortcomings of each of them. The models can be used separately, to more accurately predict the values for the required period, or a combination of them is also possible. Originality / scientific novelty. The study’s originality lies in development of methods for effectively accounting for seasonality in agricultural price data, such as using seasonal decomposition techniques or more advanced techniques that combine statistical and data science approaches. The novelty implies the implementation of real-time data processing and forecasting system allows for the timely prediction of price changes, enabling stakeholders to make more informed decisions. Practical value / implications. Forecasting potato prices holds significant practical value for various stakeholders. For farmers, accurate forecasts enable informed decisions on the optimal times to plant, harvest, and sell their crops, thereby optimising their profits. In the supply chain, distributors and retailers can use these forecasts to manage inventory more effectively and plan contracts, reducing waste and avoiding shortages. Policymakers benefit from forecasts by anticipating market fluctuations and stabilising prices, which supports both consumers and producers. For consumers, stable pricing ensures better budgeting and helps avoid sudden price spikes, making essential foods more affordable. Overall, accurate price forecasting enhances market efficiency by reducing uncertainty and aiding investors in managing risk.
- 20 September 2024
- Published by Institute of Eastern European Research and Consulting in Agricultural and Resource Economics: International Scientific E-Journal
- Vol. 10 (3) , 5-33
Open AccessTime series forecasting of price of the agricultural products using data science
Purpose. The purpose of our article is to research and forecast prices for agricultural products using the example of potato prices based on the most effective models using data science techniques. Methodology / approach. Various forecasting models are explored, starting from baseline models like decomposition and exponential smoothing models to more advanced techniques such as ARIMA, SARIMA, as well as deep learning models including neural network. The data is split into training and testing sets, and models are validated using cross-validation techniques and optimised through hyperparameter tuning. Model performance is evaluated using metrics such as MAE, MSE, RMSE, and MAPE. The selected model is then used to generate future price forecasts, with uncertainty quantified through confidence intervals. Results. The study successfully applied advanced data science techniques to forecast potato prices, leveraging a range of effective models. By analysing historical price data and using various forecasting methods, the research identified the most accurate models for predicting future price trends. The results demonstrate that the selected models can provide reliable forecasts. In particular, the results showed that the model could achieve good forecast results when applied to real problems and, thus, can be effectively used for forecasting tasks especially considering seasonality. In addition, it should be noted that the model has a higher prediction accuracy at the time intervals closest to the original data. The obtained results support using both models simultaneously for forecasting, which can compensate for the shortcomings of each of them. The models can be used separately, to more accurately predict the values for the required period, or a combination of them is also possible. Originality / scientific novelty. The study’s originality lies in development of methods for effectively accounting for seasonality in agricultural price data, such as using seasonal decomposition techniques or more advanced techniques that combine statistical and data science approaches. The novelty implies the implementation of real-time data processing and forecasting system allows for the timely prediction of price changes, enabling stakeholders to make more informed decisions. Practical value / implications. Forecasting potato prices holds significant practical value for various stakeholders. For farmers, accurate forecasts enable informed decisions on the optimal times to plant, harvest, and sell their crops, thereby optimising their profits. In the supply chain, distributors and retailers can use these forecasts to manage inventory more effectively and plan contracts, reducing waste and avoiding shortages. Policymakers benefit from forecasts by anticipating market fluctuations and stabilising prices, which supports both consumers and producers. For consumers, stable pricing ensures better budgeting and helps avoid sudden price spikes, making essential foods more affordable. Overall, accurate price forecasting enhances market efficiency by reducing uncertainty and aiding investors in managing risk.
- Open Access
- 22 August 2024
- Published by DKS Center in Efektyvna ekonomika
- No. 8
ANALYSIS AND FORECASTING THE LEVEL OF POVERTY IN UKRAINE
- 22 August 2024
- Published by DKS Center in Efektyvna ekonomika
- No. 8
Open AccessANALYSIS AND FORECASTING THE LEVEL OF POVERTY IN UKRAINE
- Open Access
- 23 February 2023
- Published by State University of Trade and Economics in Herald of Kyiv National University of Trade and Economics
- Vol. 147 (1) , 88-105
Factors of pricing of agricultural products
Вступ. Ціна є головним чинником, який безпосередньо впливає на основні результати діяльності підприємств, зокрема й аграрних. Цінова політика здатна зберегти конкурентоспроможність підприємства, забезпечити його платоспроможність і стабільність. Проблема. Ціноутворення здійснюється в складній взаємодії внутрішніх і зовнішніх чинників. Відповідна складність явища потребує включення у модель багатьох факторів, які можуть негативно вплинути на результат. Велика кількість факторів вимагає використання методів, які дадуть змогу ідентифікувати найбільш статистично значущі чинники та оцінити їх взаємозв’язок із результуючою ознакою. Мета статті – виявлення за допомогою факторного аналізу основних чинників, визначення їх впливу на формування та зміну ціни сільськогосподарської продукції. Методи: математико-статистичні (факторний аналіз, головних компонент); економіко-статистичний (множинний регресійний на основі факторних оцінок); узагальнення. Результати дослідження. За факторним аналізом та методом головних компонент визначають найбільш вагомі фактори впливу на формування цін сільськогосподарської продукції. Використовуючи різні методи зменшення розмірності, отримано три основні компоненти: пропозиція, попит, платоспроможність населення, що дало змогу виявити зв’язок між змінними та ціною без проблеми мультиколінеарності. Висновки. Використання факторного аналізу та методу головної компоненти надало можливість врахувати особливості зв’язків між показниками, що характеризують ціноутворення на картоплю, усунути мультиколінеарність між незалежними показниками, отримати менше спільних факторів, ніж вихідна кількість змінних, заробити кількісну оцінку латентної змінної. Використання ортогонального обертання сприяло більш рівномірному розподілу навантаження на всі три фактори, що спростило їх подальшу інтерпретацію та зберегло 95 % загальної первинної інформації після обертання та зменшення розмірності простих функцій, що є високим показником для практичних завдань.
- 23 February 2023
- Published by State University of Trade and Economics in Herald of Kyiv National University of Trade and Economics
- Vol. 147 (1) , 88-105
Open AccessFactors of pricing of agricultural products
Вступ. Ціна є головним чинником, який безпосередньо впливає на основні результати діяльності підприємств, зокрема й аграрних. Цінова політика здатна зберегти конкурентоспроможність підприємства, забезпечити його платоспроможність і стабільність. Проблема. Ціноутворення здійснюється в складній взаємодії внутрішніх і зовнішніх чинників. Відповідна складність явища потребує включення у модель багатьох факторів, які можуть негативно вплинути на результат. Велика кількість факторів вимагає використання методів, які дадуть змогу ідентифікувати найбільш статистично значущі чинники та оцінити їх взаємозв’язок із результуючою ознакою. Мета статті – виявлення за допомогою факторного аналізу основних чинників, визначення їх впливу на формування та зміну ціни сільськогосподарської продукції. Методи: математико-статистичні (факторний аналіз, головних компонент); економіко-статистичний (множинний регресійний на основі факторних оцінок); узагальнення. Результати дослідження. За факторним аналізом та методом головних компонент визначають найбільш вагомі фактори впливу на формування цін сільськогосподарської продукції. Використовуючи різні методи зменшення розмірності, отримано три основні компоненти: пропозиція, попит, платоспроможність населення, що дало змогу виявити зв’язок між змінними та ціною без проблеми мультиколінеарності. Висновки. Використання факторного аналізу та методу головної компоненти надало можливість врахувати особливості зв’язків між показниками, що характеризують ціноутворення на картоплю, усунути мультиколінеарність між незалежними показниками, отримати менше спільних факторів, ніж вихідна кількість змінних, заробити кількісну оцінку латентної змінної. Використання ортогонального обертання сприяло більш рівномірному розподілу навантаження на всі три фактори, що спростило їх подальшу інтерпретацію та зберегло 95 % загальної первинної інформації після обертання та зменшення розмірності простих функцій, що є високим показником для практичних завдань.
- Open Access
- 28 March 2021
- Published by Lesya Ukrainka Volyn National University in Economic journal of Lesya Ukrainka Volyn National University
- Vol. 1 (25) , 161-174
AN INTEGRATED APPROACH TO LOGISTIC RISK ASSESSMENT
The article considers theoretical and methodological aspects of logistics, namely logistics processes, logistics chain, logistics system, logistics management, logistics risk. A method of logistics management as an integrated process using the so-called network planning is proposed. This method allows a systematic approach to planning and managing the process of developing a new complex system. The process itself is seen as a single, inseparable process of interdependent operations aimed at achieving the ultimate goal. When analyzing the network model, a quantitative assessment of the time and cost of work performed. Elements of risk management in the logistics of enterprises using qualitative and quantitative analysis are considered.
- 28 March 2021
- Published by Lesya Ukrainka Volyn National University in Economic journal of Lesya Ukrainka Volyn National University
- Vol. 1 (25) , 161-174
Open AccessAN INTEGRATED APPROACH TO LOGISTIC RISK ASSESSMENT
The article considers theoretical and methodological aspects of logistics, namely logistics processes, logistics chain, logistics system, logistics management, logistics risk. A method of logistics management as an integrated process using the so-called network planning is proposed. This method allows a systematic approach to planning and managing the process of developing a new complex system. The process itself is seen as a single, inseparable process of interdependent operations aimed at achieving the ultimate goal. When analyzing the network model, a quantitative assessment of the time and cost of work performed. Elements of risk management in the logistics of enterprises using qualitative and quantitative analysis are considered.