ZSZoia Sokolovska

Zoia Sokolovska

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zoia Sokolovska has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Agent Models of Economic Diagnostics of Logistics Chains of Enterprises

    by Sokolovska Zoia

    The article considers agent simulation modeling as a basic tool for supporting management decision-making regarding the formation and diagnostics of the functioning of logistics chains of enterprises. A review of the main developments and applications existing in the field of analytical and simulation modeling of logistics processes/systems is conducted. The feasibility of using simulation modeling, especially its agent and hybrid paradigm, in research on flexible architectures of modern logistics systems is proved. Agent simulation models of logistics chains of enterprises of different architectures are presented, implemented on the software platform of the multi-approach simulation modeling system AnyLogic. The models were experimentally tested using materials from LLC "Trading House "Odeskabel". The possibilities of applied application during diagnostics are demonstrated on fragments of scenario simulation experiments conducted on the models.

  • Agent-Based Modeling in rhe Management Decision Support System of a Logistics Company

    by Zoia Sokolovska

    The article presents agent-based modeling as one of the important tools in the management decision support system of a logistics company. The processes of interaction of logistics companies with the transport exchange are studied. A review of existing developments on improving business models of exchanges, the use of modern technologies and agent modeling is carried out. A simulation model of cooperation between a typical company and an exchange is presented, built using an agent paradigm with the additional involvement of a discrete-event approach. The implementation of the model and the experimental part was carried out on the software platform of multi-approach simulation modeling AnyLogic. The possibilities of making managerial decisions on the basis of the developed simulator model are illustrated by the results of simulation experiments conducted using the materials of the logistics company Grant Logistic Group.

  • Mathematical Tools for Economic Diagnostics of Logistics Companies' Activities

    by Zoia Sokolovska

    The article presents simulation modeling as one of the mathematical tools for economic diagnostics of the activities of logistics companies. The expediency of using various paradigms of imitation and their combinations to solve a wide range of logistics problems is proved. A model for diagnosing the main economic results of the logistics company's activities for the perspective set by the experimenter, built on the basis of a combination of two simulation paradigms – discrete-event and agent-based – on the software platform of the AnyLogic multi-approach simulation modeling system is presented. The possibilities of carrying out economic diagnostics using the developed model are illustrated by fragments of the results of standard and variational simulation experiments conducted based on the materials of the logistics company Grant Logistic Group.

  • Mathematical Tools for Researching the Market of Tourist Services

    by Zoia Sokolovska, Antonina Shykhranova

    The article discusses mathematical tools for researching the market of tourist services. It is proposed to use approaches of economic and mathematical modeling, based on optimization methods and fuzzy logic, to solve urgent problems of the functioning of tourist operators and agencies. The formulation of tasks related to the choice of effective tourist routes on the basis of optimization of tour loading with minimization of costs / profit maximization and taking into account resource limitations are presented. The Markowitz model is given, adapted to the optimization of the investment portfolio of a travel company. A model for evaluating investment alternatives of a travel company for a strategic perspective using fuzzy logic methods is presented. The possibilities of using models in decision-making processes are illustrated by fragments of calculations made based on the materials of the travel company Eurotrips. The results of the work can be used in building decision support systems (DSS) in the tourism industry.

  • Hybrid Simulation Models in Management Decision Support Processes

    by Odesa Polytechnic National University, Zoia Sokolovska

    The article presents hybrid simulation modeling as an analytical basis for supporting managerial decision-making. The main concepts of building hybrid simulation models and the features of their architecture are considered. The expediency of using models of this class in the study of complex economic systems is proved. A hybrid model of production and sales activities of a pharmaceutical enterprise, built on the basis of a combination of three simulation paradigms – discrete-event, agent-based and system dynamics – on the software platform of the AnyLogic multi-approach simulation modeling system is presented. The possibilities of applying the model in decisionmaking processes and analysis of their consequences are illustrated by fragments of the results of simulation experiments based on the materials of the pharmaceutical company PrJSC "Pharmaceutical Firm "Darnitsa".

  • Open Access

    Design of an intelligent data analysis platform for pharmaceutical forecasts

    by Zoia Sokolovska, Iryna Ivchenko, Oleg Ivchenko

    This study considers the task to design a data analysis platform with predictive capabilities of neural networks. The object of research is intelligent decision-making systems built on deep learning methods. The proposed intelligent platform takes into account the specificity of working with data in the dynamic and uncertain environment of the pharmaceutical market. Its main purpose is the processing of various data formats, such as time series, regression, classification data sets to create forecasts based on various indicators. At the core of the platform architecture, along with technologies for backend and frontend development (HTML, JS, CSS, C#, .NET), MSSQL Server and TSQL for database management, are AI Microservices (Python, Flask); they are responsible for artificial intelligence services, in particular neural networks. In order to identify the optimal model, which is able to effectively solve regression problems based on the selected indicators, the study analyzed several configurations of neural networks on End-to-end machine learning platforms. Distinctive features of the architecture of the designed data analysis platform include its ability to dynamically switch between different machine learning models based on predefined indicators and criteria such as prediction accuracy and model selection. Improved interpretation of forecasts through the use of Explainable AI enables effective decision-making in the pharmaceutical industry. The functioning of the proposed instrumental decision-making base is demonstrated on the examples of forecasting trends in the consumption of pharmaceuticals by different groups in the pharmaceutical markets of different countries. Automating the model selection and prediction loss minimization process in a comprehensive data analysis platform (CDAP) improves forecast accuracy by approximately 15 % compared to traditional manually selected models.


  • Simulation Models of Pharmaceutical Logistics

    by Odesa Polytechnic National University, Zoia Sokolovska

    The article presents simulation modeling as a mathematical basis for the study of logistic systems. The object is pharmaceutical logistics – logistics chains of pharmaceutical companies. Attention is focused on the problems of functioning of domestic pharmaceutical logistics in the conditions of military realities. The expediency of using simulation modeling technologies to reproduce the changing, force majeure conditions of functioning of the supply channels of finished pharmaceutical products is substantiated. Models of one-level and two-level sales channels for pharmaceutical products, built using the discrete-event simulation paradigm on the software platform of the AnyLogic system, are presented. The results of the simulation are illustrated by fragments of simulation experiments based on the materials of the pharmaceutical company FARMAK.

  • Application of Fuzzy Decision Support Systems in IT Industry Functioning

    by Dudnyk Oleksii, Sokolovska Zoia, Alexander Gegov, Farzad Arabikhan


  • General Remarks Before the Mathematical Description Active Basic Models of Economic Dynamics

    by Odesa Polytechnic National University, Anatoly Semenov, Zoia Sokolovska, Tetiana Budoratska

    The article is devoted to the mathematical basis of research on the dynamics of economic processes at the macro level. The necessity of forming new approaches and adapting existing methods and models to the trends of the modern economy is asserted. An analysis of the basic models of economic dynamics has been carried out. It is proved that from the mathematical formulation of classical models of economic dynamics, for example, the Solow model, exponential growth of the economy follows. The results that follow from the formulation of models concern, in particular, the problem of crisis forecasting. A modification of the mathematical formulation of some well-known models of economic dynamics has been proposed in order to eliminate the inadequate exponential growth of the economy and to bring the results of modeling closer to the dynamics of real processes.

  • Mathematical Tools for Economic Diagnostics of Production and Sales Activities of Enterprises (on the Example of Fat-and-Oil Industry)

    by Odesa Polytechnic National University, Zoia Sokolovska, Oksana Klepikova

    The article presents simulation modeling as a mathematical tool for implementing economic diagnostics of industrial enterprises. The objects of the study are enterprises of the fat-andoil industry. Attention is focused on the features and problems of the functioning of the industry at the current stage in the conditions of military realities. The expediency of using the apparatus of imitation is substantiated, taking into account the uncertainty and variability of the internal and external environment of the functioning of enterprises. A model for the implementation of diagnostic studies of production and sales activities of enterprises, developed using discrete-event and agent-based simulation paradigms on the software platform of the AnyLogic system, is presented. The obtained results are illustrated by fragments of model simulation experiments.