Inventory management under stochastic demand poses significant challenges for retail warehouses, often leading to high holding costs, stockouts, and inefficient ordering practices. This study investigates the inventory control of Product A at the X Shopping Store Company’s warehouse, where the existing system lacked a reorder point and predetermined order quantity, resulting in an annual cost of 2,803.79 SAR and 12.27 sacks of stockouts. To address these issues, a stochastic simulation–optimization model was developed using Arena, integrating historical demand data and EOQ-based inventory principles. A VBA-based interface was implemented to allow managers to dynamically adjust reorder points, maximum storage, and other parameters while instantly observing the impact on order quantities, shortages, and total cost. The simulation-optimization results demonstrate that an optimal policy—with a reorder point of 30 sacks, maximum storage of 65 sacks, and order quantity of 39 sacks—reduces annual stockouts to 5 sacks and lowers total cost to 2,115.72 SAR, achieving a 24.54% cost reduction. The proposed framework provides a practical and robust decision support system for inventory management under uncertainty, enabling cost-efficient, data-driven decision-making and improved warehouse performance.