HYHanna Yarovenko

Hanna Yarovenko

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hanna Yarovenko has a total of 105 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DIGITAL GOVERNMENT AND BUSINESS FREEDOM IN UKRAINE: INTERNATIONAL BENCHMARKING AND MACHINE LEARNING ANALYSIS

    by Hanna Yarovenko

    The article studies the development of digital governance and business freedom in Ukraine in the international context. The goal is to determine the features of Ukraine’s digital development, identify countries with similar development trends, and identify key predictors of Business Freedom using machine learning methods. The GovTech Maturity Index indicators for 2020, 2022, and 2025 for 182 countries, grouped into 23 functional indicators of digital governance, served as the information basis. The study included an analysis of the dynamics of Ukraine’s indicators, clustering of countries using the K-Means method, and the use of the SHAP tool for Support Vector Regression. The results established that the overall digital capacity of Ukraine’s public sector has strengthened in the areas of digital skills, digital policy and regulation, online public services, digital identification, and civic engagement. At the same time, public investment and public administration architecture are characterized by lower or unstable values. Against the background of digital progress, the Business Freedom indicator in Ukraine decreased by approximately 2 points in 2020–2025, which is a consequence of slowing economic growth and the impact of the war. The cluster analysis placed Ukraine in the group of countries with an average level of digital governance and business freedom development. As a result, 20 closest digital-development peers were identified, including Azerbaijan, Tunisia, Kazakhstan, South Africa, and Sri Lanka. To identify significant predictors of business freedom, the SVR model was used, which explains 52.7% of the variation in Business Freedom in the training sample and 49.7% in the test sample, indicating the significance of digitalization indicators for the business environment. The SHAP analysis identified Emerging Technologies, Digital Skills, Open Source, Online Public Services, and Open Government as the most significant positive predictors of the predicted value of Business Freedom. The obtained results made it possible to characterize Ukraine’s digital development as hybrid and justify the need for a comprehensive combination of digitalization, improvement of the regulatory environment, and institutional development.

  • Digitalization and Institutional Capacity as Factors of National Security of Countries: Matrix Analysis

    by Hanna Yarovenko, Maryna Rozhkova

    The purpose of this study is to develop and validate a methodological approach for assessing the relationship between the level of digitalization and the institutional capacity of countries in the context of national security. The proposed methodology is based on the construction of a Digitalization and Institutional Security Matrix that makes it possible to identify the consistency between digital development, institutional quality, and human capital, as well as to classify countries according to their development trajectories. The methodological framework includes the calculation of an integrated Digitalization Index based on five indicators of the digital environment and an Institutional Security Index reflecting institutional quality and human capital development. Following min–max normalization, integrated indices were calculated and median values were used as threshold parameters to construct a four-quadrant matrix. An additional percentile analysis was applied to identify countries with relatively stronger or weaker positions within each quadrant. The scientific novelty of the study lies in the development of an integrated analytical framework that combines digital and institutional dimensions within a single assessment model. Unlike existing approaches, the proposed methodology makes it possible to identify structural imbalances between technological development and institutional capacity that may affect national security. The comparative analysis of country distributions for 2022 and 2024 revealed a growing asymmetry between digitalization and institutional capacity. The increase in the number of countries characterized by an imbalance between these components indicates that technological development and institutional adaptation are becoming increasingly uneven. The analysis also confirmed that the most favorable development model combines a high level of digitalization with strong institutions, whereas discrepancies between these components create additional governance and cybersecurity risks. The practical significance of the proposed approach lies in its applicability for comparative international assessments, monitoring digital transformation, identifying institutional and technological imbalances, and supporting evidence-based public policy aimed at strengthening national security under conditions of rapid digital transformation.

  • Open Access

    DIGITALISATION AND INTERNATIONAL TRADE TRANSFORMATION: A CROSS-COUNTRY CLUSTER ANALYSIS

    by Hanna Yarovenko, Heng Zhang

    The rapid development of digital technologies is reshaping international trade and strengthening the role of digitalisation in countries' competitiveness and global integration. This study aims to identify groups of countries with similar levels of digitalisation and trade transformation in goods and services and to assess the relationship between ICT development, trade transformation, and economic development. The research applies multivariate statistical analysis, including logarithmisation, standardisation, Principal Component Analysis, and K-means clustering. The optimal number of clusters was determined using the Calinski–Harabasz and Duda–Hart criteria based on 2023 data. The findings reveal a four-cluster structure for both merchandise and services trade and confirm a positive relationship between ICT development and international trade. The proposed approach can support cross-country comparisons and evidence-based digital and trade policy development.

  • Open Access

    GRU-based forecasting of conflict-related socio-economic vulnerabilities under illicit practices

    by Hanna Yarovenko, Olena Pakhnenko, Liudmyla Riabushka, Iryna Tarasenko, Viktoriia Khmurova

    Type of the article: Research ArticleAbstractThe study develops a framework for forecasting conflict-related socio-economic vulnerabilities in a cross-country sample using indicators of armed conflict risk, forced displacement, and illicit practices. The analysis uses panel data covering 135 countries over 2012–2024. The Conflict Risk Index, Refugee Load Index, and Cyber Vulnerability Index were constructed using standardized indicators and Principal Component Analysis. The Cyber Vulnerability Index is a proxy for digital exposure to cyber-related disruptions. First-difference panel regressions identified associations between conflict- and migration-related risks and socio-economic indicators. Separately, GRU neural networks were applied to forecast these indicators, while comparative quartile-based ablation and scenario-based perturbation analyses assessed the contribution and sensitivity of corruption, AML-related risk, and cyber vulnerability across country groups. Regression analysis showed that the Conflict Risk Index was statistically associated with deterioration in GDP, GDP per capita, GDP per capita growth, political stability, life expectancy, labor force dynamics, and migration balance. The Refugee Load Index was associated with positive net migration alongside weaker economic growth and lower political stability in host countries. Forecasting results were heterogeneous: adding corruption, AML-related risk, and cyber vulnerability indicators improved accuracy for several targets, but deteriorated performance for some variables and showed evidence of overfitting for GDP per capita in the conflict-risk specification. In high-conflict-risk countries, the largest forecast improvements were for life expectancy (61.02%), GDP per capita (43.96%), and net migration (10.75%); in high-refugee-load countries, they were observed for life expectancy (60.30%), political stability (38.41%), and net migration (16.20%). The framework can support early warning, resilience assessment, and crisis response.AcknowledgmentWe acknowledge with gratitude the financial support provided by the Ministry of Education and Science of Ukraine for the research project “Cybersecurity and digital transformations of the country’s wartime economy: the fight against cybercrime, corruption and the shadow sector,” state registration number 0124U000544.

  • Forecasting Illicit Practice Impacts on Economies of Conflict Countries: XGBoost Approach

    by Hanna Yarovenko, Viktoriia Hurochkina, Aneta Cugova, Kseniia Mohylna

    The article examines the impact of illegal practices on economic growth in countries experiencing armed conflict in the context of increasing global geopolitical instability. The study aims to develop and test a predictive approach to quantitatively assess the impact of corruption, money laundering, and cyber risks on the economic growth dynamics of conflict countries using modern machine learning methods. The empirical basis of the study is panel data for 83 countries during 2012–2024. The dependent variable is the logarithmic growth rate of GDP per capita, and the key influencing factors are indicators of corruption, money laundering risk, cybersecurity, and conflict intensity. The methodological basis is the extreme gradient boosting (XGBoost) algorithm, supplemented by the construction of lag variables, interactions for conflict countries, feature importance and SHAP interpretation methods, and scenario analysis. The scientific novelty of the study lies in combining machine learning with cross-country panel data to forecast economic growth in conflict conditions, as well as in identifying nonlinear, asymmetric, and delayed effects of illegal practices. Unlike traditional econometric approaches, the proposed model allows for complex interrelationships among institutional, financial, and security factors, as well as the heterogeneity in responses across countries’ economies. The results show that all XGBoost models achieve stable, high-quality forecasting, with the most accurate results from a comprehensive model that considers all types of illegal practices. It was found that economic growth in conflict countries exhibits significant inertia, while the effects of corruption, money laundering, and cybersecurity manifest with a time lag. SHAP analysis revealed contradictory, context-dependent effects: corruption and money laundering can partially compensate for institutional weakness in the short term, while cybersecurity deterioration mostly has a negative impact on economic dynamics. The practical significance of the results lies in the possibility of using the proposed approach to support decisions in the areas of anti-corruption policy, financial monitoring, and cybersecurity, as well as formulating strategies for economic stabilization and post-conflict recovery, considering the specifics of individual countries and development scenarios.


  • Top Cited Papers
    Open Access

    Transformational Interlinkages between Ukraine’s Economic and Demographics Potential: Implications for Public Governance Based on the Analysis of Migration, Public Health, and Citizens’ Well-Being Shifts

    by Kateryna Zahorodnia, Zhanna Tverdovska, Hannah Yarovenko, Maxim Shubenko, Null

    Demography is one of the key factors in shaping the state’s economic potential and a strategic priority for public governance, as population size, age structure, birth and mortality rates, and migration processes directly dictate the sustainability of internal economic and administrative frameworks. At the same time, economic stability and the material well-being of citizens create a favorable basis for increasing the birth rate, curbing emigration, and improving the quality of human capital. Negative economic trends, especially under the conditions of military conflict, provoke increased migration processes, a reduction in labor resources, and a deepening of social problems. The article is devoted to modeling the interdependence between demographic processes and the economic development of Ukraine for the period 1995–2023. A comparative assessment of the strength and direction of influence of individual factors, as well as a quality check of the constructed models, is carried out. The following parameters are included in the economic and mathematical modelling: net migration rates, population growth, unemployment rate, total annual freshwater withdrawal (% of domestic resources), real interest rate, GDP per capita, and adolescent fertility rate. The impact of these factors is multifaceted: the findings reveal that the depletion of human capital through migration creates structural imbalances in the labor market, while the correlation between adolescent fertility and GDP highlights the need for targeted social interventions. Ultimately, the analysis demonstrates that the effective transformation of these interlinkages depends on the capacity of public governance to implement adaptive policies that harmonize economic incentives with demographic security to ensure long-term national resilience.


  • Open Access

    Measuring Digital Government’s Impact on Business Freedom: An Econometric and Machine Learning Approach

    by Hanna Yarovenko, Zuzana Kubaščikova, Vadim H. Grigoryan, Meiramgul Dulat, Leonid Taraniuk, Null

    Digital transformation of public administration increasingly intersects with business freedom within institutional environments shaped by transparency, responsible governance, institutional accountability, and the quality of state–business interaction. Previous research has extensively examined digital government in relation to administrative efficiency, innovation, and economic growth yet has provided limited cross-country evidence on how the transparency and accountability of multidimensional digital governance are associated with the institutional conditions under which businesses operate. This study assesses the relationship between digital government maturity and business freedom and determines which dimensions of government technology have the strongest statistical and predictive relevance. The empirical analysis covers 182 countries in 2020, 2022, and 2025, combining the Business Freedom Index with 43 World Bank government technology indicators aggregated into 23 composite dimensions. The methodology integrates descriptive statistics, correlation and multicollinearity analysis, the Kruskal–Wallis test with pairwise comparisons, fixed-effects panel regression with Arellano robust standard errors, eight predictive algorithms, permutation feature importance, Shapley additive explanations, and regional analysis implemented in Python and Gretl. The final fixed-effects model identifies Digital Policy and Regulation as exhibiting the strongest positive within-country association, with a coefficient of 3.271 and a probability value below 0.001, while Debt Management and Digital Identification have coefficients of −1.991 and −1.102, indicating that the regulatory and institutional dimensions of digitalization are particularly relevant to variation in business freedom. Support vector regression achieves a test coefficient of determination of 0.497 with a train–test R² gap of only 0.031, whereas the inclusion of regional affiliation raises the test coefficient of determination to 0.603 and reduces the test root mean squared error from 12.55 to 11.14, indicating that broader regional context provides substantial additional predictive information. Permutation and Shapley-based interpretation identify Online Public Services, Digital Tax, Emerging Technologies, Government Architecture, Employment Services, and Open Government among the most influential predictors, while Europe reaches a permutation importance of 0.241, substantially exceeding that of any individual digital-government component. The findings provide an empirical basis for strengthening transparency, responsible governance, and institutional accountability in digital public administration and for future research on how ethically grounded state–business interaction can translate government technology maturity into more favorable conditions for business freedom.

  • Machine-Learning-Based Forecasting of Stock-Price Dynamics: Implications for Investment Analysis and Financial Risk Management

    by Hanna Yarovenko, Ivan Peichev

    Modern equity markets are increasingly exposed to technological, geopolitical, macroeconomic, and behavioral shocks, which strengthens the need for forecasting tools capable of processing non-stationary, noisy, and autocorrelated financial data. Despite the extensive literature on stock-price forecasting using machine-learning techniques, limited attention has been paid to the comparative performance of recurrent neural-network architectures when applied to highly influential technology stocks within the context of investment analysis and financial risk management, particularly under conditions of persistent non-stationarity and market uncertainty. This study aims to develop and empirically verify a machine-learning-based approach to forecasting stock-price dynamics using historical adjusted closing prices of Apple Inc. (AAPL) and Microsoft Corporation (MSFT), with particular attention to the accuracy, reliability, and practical relevance of recurrent neural-network models for investment analysis and financial risk management. The empirical analysis used weekly adjusted closing prices from Yahoo Finance, covering 263 observations for each stock, and combined exploratory data analysis, stationarity and autocorrelation testing, sliding-window transformation, MinMax normalization, chronological train-test-validation splitting, and gated recurrent unit (GRU-based recurrent neural-network modeling). The descriptive results show that MSFT had a higher mean adjusted closing price than AAPL (254.33 compared with 132.12) and stronger variability, with a standard deviation of 79.24 compared with 43.44. The augmented Dickey–Fuller (ADF) test confirmed non-stationarity in both series, with p-values of 0.4594 for AAPL and 0.9229 for MSFT, while autocorrelation analysis indicated strong dependence between current and past price levels. The forecasting model achieved high relative accuracy, with forecast accuracy of 96.63% for AAPL and 97.45% for MSFT. The model exhibited lower error levels for AAPL in terms of mean squared error (MSE) and mean absolute error (MAE), with values of 55.80 and 6.11, respectively, whereas MSFT showed higher MSE and MAE values of 144.44 and 9.41, despite achieving lower MAPE and higher forecast accuracy, reflecting stronger volatility and greater forecasting complexity in the MSFT series. The findings open new avenues for integrating machine-learning forecasting systems into portfolio management, risk-monitoring frameworks, and data-driven investment decision-making, while also providing a foundation for future research on explainable artificial intelligence, multi-asset forecasting models, and advanced financial-risk analytics in increasingly volatile capital markets.


  • Digital transformation and economic development in Europe: Classical and machine-oriented approaches

    by Hanna Yarovenko, Dmytro Ohol, Laura Ashirbekova, József Popp

    The article analyses the influence of digital transformation on the economic development of European countries using a combination of classical econometric approaches and machine learning algorithms. The study uses 85 indicators of digital economy and society for 27 countries during 2017–2022, covering various aspects of digitalisation: human capital, digital infrastructure, broadband coverage, ICT specialisation, business innovation activity, etc. After preliminary data processing, multicollinearity diagnostics, and hierarchical clustering, factor analysis identified four latent components: digital competence and business innovation, digital infrastructure and connectivity, broadband coverage and penetration, ICT human resources and specialisation. To evaluate the relationships between digital factors and GDP per capita, pooled OLS, ridge, lasso regressions, random forest, XGBoost, and support vector regression models were applied. The highest forecasting accuracy was demonstrated by the SVR model, which provided minimal error values and effectively captured nonlinear dependencies in panel data. Feature-importance analysis revealed the leading role of digital competence and business innovation, as well as the considerable cross-country heterogeneity of digital drivers of economic development. The results confirm the need for developing differentiated digital-policy strategies and provide the basis for further advancement of causal and spatial modelling of the digital economy.