Статті КМЕУіСГД (ДМетІ)

Permanent URI for this collectionhttps://crust.ust.edu.ua/handle/123456789/22104

ENG: Articles

Browse

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Item type:Item,
    Smart Analytics Tools for Supporting Management Decisions in the Field of Production System Management at Enterprises in the Context of Sustainable Development
    (Fintechalliance LLC, Chayky Village, 2026) Ivanova, Maryna; Kaut, Olga V.; Vyshnevska, Mariia K.; Boichenko, Mykola; Papizh, Yuliia; Dubiei, Yuliia
    ENG: This article addresses the growing importance of smart analytics as a technical tool and fundamental intellectual asset ensuring sustainable development, resilience, and competitiveness of enterprises under digital transformation. The paper examines the Smart Data Adaptive Cycle (SDAC) model, which offers a continuous closed-loop decision-making process in a digital manufacturing environment. The model integrates informational, financial, and cognitive components using self-learning mechanisms and the human-in-the-loop principle. The purpose of the work is to examine the specifics of ensuring sustainable development in an enterprise through managerial decision-making using smart analytics tools in the management of production systems. The study applies general and specialized methods, including a scenario-based approach to determine the relationship between information entropy and economic value added (EVA), a case study for empirical validation of the SDAC model at a metallurgical enterprise, discounting for economic feasibility, and a systematic approach to constructing the conceptual model. A comparative scenario analysis of ex-post, partial, and full SDAC models was conducted. The main results show that the SDAC model integrates information theory and value-based management (VBM) into a single adaptive cycle. The findings demonstrate that entropy analysis allows for the formalization of uncertainty in the production environment (BANI context), providing a quantitative ex-ante risk assessment that is more effective than traditional retrospective methods. Empirical modeling confirms that integrating smart analytics into production management enables the maximization of EVA. Practical testing at a metallurgical enterprise demonstrated the model’s ability to reduce equipment downtime to 8.2%, defect rates to 3.6%, and carbon emissions to 190 kg CO₂/t, while increasing labor productivity. The conclusions confirm the effectiveness of the SDAC model as a tool for improving managerial decision-making and ensuring sustainable enterprise development. Future research includes scaling the model to other sectors and integrating it into approaches for assessing nonlinear extreme events (black swan events).