OPTIMIZATION OF FUZZY INVENTORY MANAGEMENT IN INDUSTRIAL PROCESSES USING DEEP LEARNING ALGORITHMS: A HYBRID APPROACH FOR ENHANCING DEMAND FORECASTING AND SUPPLY CHAIN EFFICIENCY

In today’s dynamic business landscape, effective inventory management is essential for minimizing costs and maximizing profitability. Traditional models like EOQ and JIT often fall short in handling demand and supply uncertainties due to their reliance on precise data. This paper introduces a novel approach that combines fuzzy logic and deep learning to address these limitations. Fuzzy logic offers a robust framework for decisionmaking under uncertainty, while deep learning improves predictive accuracy by identifying complex patterns in historical data. By transforming data into fuzzy sets and applying neural networks for demand forecasting, the proposed model optimizes inventory levels to reduce costs and prevent stockouts. A mathematical model and algorithmic implementation demonstrate the approach’s effectiveness and a numerical example highlights improvements in inventory control, including reduced holding costs. This study underscores the potential of integrating AI techniques for adaptive, data-driven inventory management with broad applications across various industrial processes.