PREDICTIVE MODELS IN LOGISTICS: THE USE OF ARTIFICIAL INTELLIGENCE IN THE MANAGEMENT OF PURCHASING, INVENTORY, AND DEMAND

Abstract

The increasing incorporation of technologies based on artificial intelligence has generated remarkable transformations in logistics management, especially regarding the application of predictive models used in functions related to purchasing, inventory management, and demand analysis. These changes have enabled improvements in logistics processes, optimizing operations and bringing greater efficiency to the execution of these essential activities. In this context, the use of data and the adoption of analytical algorithms have allowed a significant increase in forecasting accuracy, while also improving the coordination of different operations within an organization. Consequently, this has favored decision-making processes that are more consistent, particularly in an organizational environment that is becoming increasingly dynamic and integrated, reflecting the complexity and interaction among various areas and processes. The general objective of this research is to analyze the application of predictive models based on artificial intelligence in the management of purchasing, inventory, and demand, aiming at the optimization of logistics processes and the improvement of decision-making. Regarding the methodology, a qualitative approach was adopted, focused on a detailed understanding of the implications of using artificial intelligence in logistics. As a research procedure, a literature review was conducted through the systematic analysis of relevant scientific publications, enabling the construction of a consistent theoretical basis for the development of the study. In summary, the research demonstrated that the application of predictive models based on artificial intelligence in the management of purchasing, inventory, and demand contributes to the optimization of logistics processes and to improved decision-making by promoting greater forecasting accuracy, better resource allocation, and higher operational efficiency throughout the supply chain.