EOQ Based Inventory Optimization with Partial Backordering and Demand Uncertainty in Manufacturing

Abstract

Inventory management is one of the important aspects in manufacturing systems, especially in the face of demand uncertainty and lead time variability. The classic Economic Order Quantity (EOQ) model is often assumed with constant demand and fixed lead times that do not always reflect the complexity of the real world. This research develops a more adaptive EOQ-Partial Backordering model by integrating a dynamic demand response mechanism as well as a lead time-based ordering strategy, in order to improve the resilience of inventory systems in manufacturing systems. The proposed model is designed to minimize the total inventory cost, by considering the balance between holding cost, backordering cost, and ordering cost. In contrast to previous models, this approach systematically measures between immediate demand fulfillment and delayed fulfillment, thus enabling more flexible inventory decisions. The evaluation of the model was conducted using sensitivity analysis and Monte Carlo simulation, by testing different scenarios of demand volatility and variations in the proportion of backorders. The results show that considering partial backordering in the EOQ framework will result in a better inventory policy, reduce excess stock and improve cost effectiveness. On the other hand, this study also considers the impact of demand fluctuations on the optimal ordering quantity and provides practical knowledge and can be a strategic reference for inventory managers in the manufacturing industry. The main contribution of this research in inventory theory is to bridge the gap between deterministic EOQ models and stochastic demand dynamics in the real world, while offering an applicable decision-making tool for more efficient inventory management and better supply chain resilience.