DEVELOPMENT OF A CLASSIFICATION MODEL FOR A MANUFACTURING ENTERPRISE BASED ON THE DECISION TREE METHOD

In today's rapidly advancing technological environment and continuously transforming industrial systems, the search for meaningful patterns and hidden knowledge beyond traditional data analysis methods has become increasingly important. This need plays a significant role in supporting stakeholders, especially in the areas of operational decision-making, forecasting, and production management. For a manufacturing enterprise, timely and well-grounded decisions are essential for improving productivity, ensuring product quality, reducing risks, and maintaining sustainable development. Therefore, it is important to identify effective Decision Tree (DT) techniques for solving classification problems and to determine their practical applicability in real production conditions. The integration of large-scale data processing with Machine Learning (ML) provides a valuable basis for developing data-driven models in industrial enterprises. In this context, the present study aims to provide a methodological approach for building an efficient classification model for a manufacturing enterprise based on the Decision Tree method. Particular attention is given to the selection of informative features, the formation of classification rules, and the practical relevance of the constructed model for production decision-making. By using the analytical potential of machine learning and the combined efforts of researchers, data analysts, and production specialists, the study seeks to obtain more accurate, understandable, and practically applicable results. At the same time, it is important to recognize that the usefulness of a classification model depends not only on its mathematical accuracy, but also on how clearly its results can be interpreted by decision-makers. In the context of industrial management, a model should remain accessible, comprehensible, and suitable for practical application by managers and specialists who are directly involved in production processes. In this regard, the study emphasizes the interpretability of the Decision Tree model and its value as a tool that can support effective analysis, improve decision-making quality, and contribute to the overall efficiency and competitiveness of the manufacturing enterprise.