NDNataliia Datsenko

Nataliia Datsenko

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nataliia Datsenko has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    ЕКОНОМЕТРИЧНЕ МОДЕЛЮВАННЯ ФАКТОРІВ ЕКОНОМІЧНОГО ЗРОСТАННЯ НА ОСНОВІ ПАНЕЛЬНИХ ДАНИХ

    by Олена Качан, Тетяна Кмитюк, Наталія Даценко

    Економічне зростання є ключовим показником розвитку країни та предметом досліджень у макроекономіці. Вивчення факторів, що впливають на рівень ВВП на душу населення, дозволяє розробити ефективні стратегії економічної політики та підвищити добробут населення. Сучасні методи економетричного аналізу, зокрема панельні, дають змогу отримати дані як часові тенденції, так і індивідуальні особливості окремих країн. Це особливо важливо при порівнянні держав із дуже соціально-економічними та політичними умовами. У статті досліджуються фактори економічного зростання на основі економетричного моделювання панельних даних для 18 країн за період 2002–2020 рр. Результативним показником обрано ВВП на душу населення, а основними пояснювальними змінними є індикатори зовнішньоекономічної діяльності (частка експорту у ВВП та торгове сальдо на душу населення) та якість інститутів державного управління (Worldwide Governance Indicators). Для врахування індивідуальних особливостей країн застосовано панельні моделі з фіксованими та випадковими ефектами. Вибір найбільш адекватної специфікації моделі здійснювався за допомогою тестів Вальда, Бреуша–Пагана та Хаусмана. Результати показують, що показники якості державного управління та ефективності зовнішньоекономічної діяльності є статистично значущими детермінантами ВВП на душу населення, однак їх вплив різниться у різних групах країн. Дослідження підкреслює важливість поєднання економічних і інституційних факторів для забезпечення сталого економічного зростання. Застосовані методи демонструють переваги аналізу панельних даних для підвищення точності оцінок та врахування латентних, специфічних для кожної країни чинників.


  • Open Access

    ФОРМУВАННЯ ІННОВАЦІЙНОЇ МОДЕЛІ РОЗВИТКУ ПРОМИСЛОВИХ ПІДПРИЄМСТВ

    by Олена Терентьєва, Наталія Даценко

    Modern industry is undergoing a profound and systemic paradigm shift driven by the convergence of advanced Industry 4.0 technologies, the global transition toward servitization, and heightened geopolitical instability. These processes have significantly increased the importance of innovative development integrated with digital technologies as a decisive factor for maintaining the competitiveness and resilience of industrial enterprises. The article examines the conceptual foundations and practical challenges of digital transformation, emphasizing the need for a holistic and adaptive approach to innovation management. The main barriers identified include technological fragmentation, insufficient digital maturity, organizational resistance to change, and limited interoperability between systems. To address these challenges, the paper proposes a synergistic innovation model as a structured, dynamic framework for industrial development. The model is based on four interconnected pillars: an open digital ecosystem that supports collaboration and co-creation; intelligent infrastructure integrating Industry 4.0 tools such as IoT, AI, and cloud computing; organizational flexibility that enables rapid adaptation; and a data-driven culture fostering evidence-based decision-making. For practical implementation, a four-phase roadmap is developed, including strategic diagnostics, detailed design, pilot implementation, and large-scale organizational transformation. The model operates on the principles of flexibility, customer orientation, and continuous learning, ensuring alignment between internal capabilities and external innovation dynamics. The article also provides practical recommendations for minimizing risks during the transition, including strategic licensing of proven digital solutions, the use of agile methodologies, and the Lean Startup approach (MVP testing). The synergistic innovation model is shown to be an essential conceptual and practical framework for digital transformation, allowing enterprises to evolve into continuously learning, adaptable systems that effectively integrate technological progress with strategic management.

  • Development of smart economy: international assessment and implementation prospects in Ukraine

    by Tetiana Orekhova, Iryna Kalenyuk, Iryna Uninets, Nataliia Datsenko

    The article substantiates the need for smart economy research not only at the level of cities (localities), but also at the level of the national economy. A methodical approach to assessing the development of the smart economy at the country level is proposed. On the basis of the systematization of the existing assessments of the development of the smart economy at the city level and the generalization of the most comprehensive approaches to the assessment of the progress of countries, successive steps for the assessment of the development of the smart economy at the national level have been determined. The ranking of countries according to the main aspects of smart economy was determined by summarizing the existing approaches for assessing the progress of countries (the most well-known complex and specialized indices). The results of the ranking of cities according to various indices during 2018-2020 are summarized. The obtained results are adjusted taking into account the number of the population living in smart cities relative to the entire population of the country. The results of the analysis were visualized and the countries with the greatest progress in the advancement of the smart economy were identified. Proposals regarding the prospective development of the smart economy and smart cities in the context of modern challenges: the pandemic and the post-war recovery of the Ukrainian economy have been formulated.

  • Machine learning approaches for financial time series forecasting

    by Vasily Derbentsev, Andriy Matviychuk, Nataliia Datsenko, Vitalii Bezkorovainyi, Albert Azaryan

    This paper is discusses the problems of the short-term forecasting of financial time series using supervised machine learning (ML) approach. For this goal, we applied several the most powerful methods including Support Vector Machine (SVM), Multilayer Perceptron (MLP), Random Forests (RF) and Stochastic Gradient Boosting Machine (SGBM). As dataset were selected the daily close prices of two stock index: SP 500 and NASDAQ, two the most capitalized cryptocurrencies: Bitcoin (BTC), Ethereum (ETH), and exchange rate of EUR-USD. As features we used only the past price information. To check the efficiency of these models we made out-of-sample forecast for selected time series by using one step ahead technique. The accuracy rates of the forecasted prices by using ML models were calculated. The results verify the applicability of the ML approach for the forecasting of financial time series. The best out of sample accuracy of short-term prediction daily close prices for selected time series obtained by SGBM and MLP in terms of Mean Absolute Percentage Error (MAPE) was within 0.46-3.71 %. Our results are comparable with accuracy obtained by Deep learning approaches.


  • Open Access

    Forecasting cryptocurrency prices time series using machine learning approach

    by Vasily Derbentsev, Natalia Datsenko, Olga Stepanenko, Vitaly Bezkorovainyi

    This paper describes the construction of the short-term forecasting model of cryptocurrencies’ prices using machine learning approach. The modified model of Binary Auto Regressive Tree (BART) is adapted from the standard models of regression trees and the data of the time series. BART combines the classic algorithm classification and regression trees (C&RT) and autoregressive models ARIMA. Using the BART model, we made a short-term forecast (from 5 to 30 days) for the 3 most capitalized cryptocurrencies: Bitcoin, Ethereum and Ripple. We found that the proposed approach was more accurate than the ARIMA-ARFIMA models in forecasting cryptocurrencies time series both in the periods of slow rising (falling) and in the periods of transition dynamics (change of trend).