<![CDATA[The inventory model provides a mathematical foundation for estimating total costs in managing product flow within a supply chain. As modern supply chains involve multiple decision makers with potentially conflicting objectives, multi-echelon inventory systems require both cost optimization and strategic coordination. Conventional optimization methods are often insufficient to capture these strategic interactions. To address this challenge, this study develops a hybrid model integrating game-theoretic analysis with a Genetic Algorithm (GA) to optimize decision-making in multi-echelon inventory systems. The main contribution of this study lies in integrating game-theoretic equilibrium concepts with a genetic algorithm framework to provide a unified analytical–computational approach for two-echelon inventory decision-making. Game theory represents the strategic behavior among supply chain actors through equilibrium concepts such as Nash and Stackelberg equilibria, while the GA efficiently explores high-dimensional decision spaces to obtain near-optimal solutions. The integration of game-theoretic equilibrium concepts with a genetic algorithm framework allows the resulting solutions to satisfy equilibrium conditions while remaining computationally tractable. This hybrid framework provides a more realistic representation of supply chain decision-making under competitive or cooperative settings. The results demonstrate that the proposed approach enhances the performance of classical game-theoretic inventory models, offering a robust tool for optimizing inventory strategies in complex supply chain environments. The results demonstrate improvements in total inventory cost and coordination efficiency across the vendor–buyer system under different equilibrium schemes. However, this study is limited to a two-echelon deterministic inventory structure with numerical illustrations]]>
