AI-Driven Hybrid Fuzzy Optimization for Sustainable Inventory Management

Sustainable inventory management has become a critical challenge for organizations operating in uncertain and dynamic supply chain environments. Traditional inventory models are unable to effectively manage imprecise demand patterns, fluctuating operational costs, and environmental sustainability requirements simultaneously. This paper proposes an AI-driven hybrid fuzzy optimization framework for sustainable inventory management. The proposed model integrates fuzzy logic, machine learning-based demand prediction, and hybrid metaheuristic optimization to minimize total inventory cost while reducing environmental impact. Fuzzy set theory is used to represent uncertainty in demand and cost parameters, while Artificial Intelligence (AI) techniques are employed for adaptive demand forecasting. A hybrid optimization algorithm combining Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) is utilized to obtain optimal inventory policies. Numerical experiments using realistic hypothetical data demonstrate that the proposed framework outperforms classical EOQ, fuzzy EOQ, and standalone optimization models in terms of total cost reduction, shortage minimization, and sustainability performance. The study highlights the significance of integrating AI and fuzzy optimization for intelligent and sustainable inventory decision-making.