Oleksandr Artiushenko

Dr. Oleksandr Artiushenko

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
TZTetiana Zatonatska
Tetiana Zatonatska
Oleksandr DluhopolskyiOleksandr Dluhopolskyi
Oleksandr Dluhopolskyi
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
Cristina LopesCristina Lopes
Cristina Lopes
AIAnzhela Ignatyuk
Anzhela Ignatyuk
OLOlena Liubkina
Olena Liubkina
This study examines the application of ensemble machine learning methods for identifying and flagging potentially risky transactions in military public procurement in Ukraine, a sector characterized by elevated financial and security sensitivity and limited capacity for comprehensive ex post control. Using an integrated dataset of procurement procedures conducted between 2021 and 2025, enriched with 56 financial, economic, and behavioral indicators of suppliers, the study develops and compares standard logistic and LASSO-penalized regression as econometric benchmarks, Random Forest, XGBoost, XGBoost with SMOTE balancing, and CatBoost classification models. The target variable is defined on the basis of officially detected violations identified through state monitoring. Model performance is evaluated using standard binary classification metrics, with particular emphasis on recall. Model uncertainty and predictive robustness are addressed through partial dependence analysis, temporal stability assessment, and out-of-sample residual diagnostics. The results indicate that the CatBoost model demonstrates the most balanced performance across evaluation measures. Feature importance analysis identifies expected contract value, procurement method, CPV code, and suppliers’ financial capacity as significant determinants of procurement-related risk. The findings provide empirical evidence on the usefulness of risk-oriented machine learning tools in supporting earlier detection and monitoring of irregularities in military procurement.

17 September 2025
Verified
Conference Paper
Closed access
TZTetiana Zatonatska
Tetiana Zatonatska
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
OLOlena Liashenko
Olena Liashenko
ASAlim Syzov
Alim Syzov
SDSerhiy Dyachenko
Serhiy Dyachenko
KHKira Horiacheva
Kira Horiacheva
This paper examines the use of artificial intelligence (AI) in public procurement of dual-use goods, emphasizing the need to automate the identification of risky procurements and enhance state oversight efficiency. The paper solved two main tasks: development of an algorithm for analysing public procurement based on the Common Procurement Vocabulary (CPV) codes and lot descriptions, and training an AI model to classify risky procurements.The analysis is based on a sample of over 72,000 public procurements by the defence and security sector of Ukraine (2001-2025), as well as data on dual-use goods. The Term Frequency-Inverse Document Frequency (TF-IDF) method combined with cosine similarity was used to process textual data, identifying lots likely related to dual-use goods. An expanded procurement sample, including additional characteristics of suppliers and lot parameters, was used to train Naive Bayesian, Random Forest, and Extreme Gradient Boosting (XGBoost) classifiers. XGBoost demonstrated the best accuracy. In the paper, we also developed an algorithm for using blockchain to store procurement data.

1 January 2024 in Visnyk Taras Shevchenko National University of Kyiv. Military-Special Sciences
Verified
Journal Article
Open access
PDF file
SDSerhii Dyachenko
Serhii Dyachenko
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
СДСергій Дяченко
Сергій Дяченко
B a c k g r o u n d . Optimisation of defence expenditures is critical for ensuring the combat capability of the military and maintaining national security. Ukraine is increasing its expenditure on armaments and military equipment, which requires efficient management of budgetary resources to achieve maximum impact. Effective management of budgetary resources is crucial not only for ensuring the combat capability of military formations, but also for maintaining national security. M e t h o d s . The article uses the AHP method with the use of pairwise comparisons and the Saaty scale to evaluate the criteria within the BOCR concept (benefits, costs, opportunities, risks). R e s u l t s . The article develops a decision-making model based on the AHP concept to help in the evaluation and selection of suppliers. The model evaluates suppliers using a set of criteria grouped into four categories: Benefits, Costs, Opportunities and Risks (BOCR). Each criterion, such as price, product quality, delivery time and supplier reliability, was assigned a weight using a pairwise comparison matrix based on the Saaty scale. The AHP approach allowed both quantitative and qualitative criteria to be integrated into the decision-making process. After evaluating the three suppliers, Supplier 1 was identified as the most suitable option with the highest BOCR of 1.033. C o n c l u s i o n s . The research conducted in this article has shown that the AHP-based decision-making model is an effective tool for optimising defence expenditure and improving procurement processes. Through the application of the BOCR concept, the model balances positive and negative factors, ensuring a transparent and efficient decision-making process. The use of pairwise comparisons ensures consistency of judgement and allows decision makers to rank alternatives in a systematic way. The paper emphasises the adaptability of the model to different operating environments: Microsoft Excel is used for data analysis and implementation, but programming languages can also be used. The results of the study demonstrate that multi-criteria optimisation methods such as AHP are valuable tools for optimisation in defence expenditure management, including the selection of suppliers of goods, works and services.

1 January 2023 in Visnyk Taras Shevchenko National University of Kyiv. Military-Special Sciences
Verified
Journal Article
Open access
PDF file
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
B a c k g r o u n d . The relevance of this article lies in the fact that, in conditions of limited resources, the optimal allocation of financial resources is of great importance for the effective functioning of the state, including military units, as components of the budget system. The purpose of this study is to apply linear programming methods in combination with modern technologies to select the optimal allocation of resources to test a tool that will help institutions, including military units, use financial resources more efficiently and achieve maximum readiness and capabilities with limited budgetary resources. The object of the research. The object of study of this article is the process of financial support of military units as components of the state budget system. M e t h o d s . In the course of the research, the following methods of scientific the following methods of scientific cognition: logical, induction, deduction, classification, grouping - in the study and mechanism of financial support of military units; methods of economic and mathematical modeling, linear programming, formalization - in the formation of the model, its testing on data and development of proposals for its further application. R e s u l t s . The article considers the concept of a military unit from two main aspects: as a military unit and as a budgetary institution managing budgetary funds. Linear programming and modelling methods are used with the help of computer tools and in combination with modern technologies such as Python programming, Google Collaboratory, Jupyter notebook environment, Gurobi optimization library. Based on the results of the study, a financial resource allocation scheme was formed that maximizes the benefit from the use of a limited financial resource. C o n c l u s i o n s . The article explores the possibility of using linear programming methods to determine the optimal allocation of limited financial resources within a military organization among various activities required to meet a specific set of military unit needs, with potential alternative options (groups of options). As a result of the model optimization, the predetermined capabilities of the military unit were satisfied as follows: A – 100%, B – 0%, C – 71%, D – 90%, with the distribution of the financial resource (budget) appearing as follows: A – 29%, B – 0%, C – 37.5%, D – 33.5%, model also ensures 100% utilization of the designated financial resource.

29 January 2025 in Вісник Хмельницького національного університету. Економічні науки
Verified
Journal Article
Open access
PDF file
АSАlim Syzov
Аlim Syzov
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
SDSerhiy Dyachenko
Serhiy Dyachenko
The paper analyses the current state of the financial support system of the Armed Forces of Ukraine, focusing on the growing challenges and limited budgetary resources. Particular emphasis is placed on the need to introduce multi-criteria optimization methods to improve the efficiency of budget management. The main objective of the paper is to assess the cost-effectiveness of implementing design solutions in the financial support system of military units of the Armed Forces of Ukraine, which allows optimizing costs, minimizing risks and increasing the level of responsibility in budget planning. The paper is based on the results of an expert survey involving more than 60 representatives of budget holders at various levels of management of the financial support system of the Armed Forces of Ukraine. The survey helped to identify key areas that need to be optimized, including monitoring and accounting of the status of budget execution, reporting, efficient allocation of limited resources between areas and evaluation of suppliers' proposals in public and defense procurement. A method for evaluating project solutions in the system of financial support of the Armed Forces of Ukraine has been developed. The methodology for analyzing alternative solutions is based on the TOPSIS method (Technique for Order of Preference by Similarity to Ideal Solution), which allows taking into account numerous evaluation criteria and provides an objective ranking of possible options. The results of the calculations show that the most effective alternative is V1, which includes the implementation of software for process automation of the following blocks: a reference book of regulations, tools for allocating limited budget funds between certain areas, and for assessing the effectiveness of expenditures. When calculating according to the developed methodology, based on expert judgements, the expected savings in the institution's budget were obtained at the level of 12-15%.

17 March 2023 in Grail of Science
Verified
Journal Article
Open access
PDF file
Oleksandr ArtiushenkoOleksandr Artiushenko
Oleksandr Artiushenko
The article carries out a scientific and methodological analysis of the role of institutional theory in the budget research. It has particular relevance in the current conditions of transformation. The problems of establishing the budget institution are mainly related to institutional uncertainty regarding the development and evolution of society and the role and place of the budget in this process. The study of military funding as a component of the country's budget system necessitates the use of a methodological toolkit, the foundation of which is the theory of institutionalism. Institutionalism as a theoretical framework makes it possible to fully and objectively grasp the essence of socio-economic processes, particularly those that take place in the sphere of budgeting.