Abstract
<jats:p>This article examines current challenges in improving the efficiency of logistics management (hereinafter referred to as LMS) in the territorial divisions of the Russian Ministry of Emergency Situations. The analysis revealed systemic limitations of the existing management model, such as reactive planning, a lack of substantiated data for decision-making, fragmented accounting systems, and a low degree of demand forecasting. As a solution, the concept and architecture of the Intelligent System for Supporting Management Decisions in Logistics (ISPUR MTO) is proposed – a centralized platform based on big data consolidation and machine learning methods. The authors describe the key components of the system: a module for predictive analytics of the technical condition of the fire-fighting and rescue equipment fleet; an optimization module for planning expenses on fuel and lubricants and spare parts; and a recommendation module that generates management decision scenarios based on the analysis of historical data, the current situation, and predictive models. The methodological basis for the development was the theory of managing complex organizational and technical systems, a comparative analysis of the experience of implementing predictive maintenance in logistics and industrial complexes, and the formalization of decision-making processes using simulation modeling methods. The implementation of the proposed concept will enable the transition from a costly and reactive logistics model to a cost-effective and proactive one, providing unit managers with objective, verified data and predictive scenarios for resource optimization, budget planning, and maintaining high operational readiness of forces.</jats:p>