Data-Driven Robust Optimization in Supply Chain Inventory Management Considering Demand Fluctuations

Data-Driven Robust Optimization in Supply Chain Inventory Management Considering Demand Fluctuations

Ehsan Sheikhasadi1

1) Master of science student, K.N Toosi University of Technology, Tehran, Iran.

IOI Code : ABZE-ABHHBK
Publication : 5th International Congress on Civil Engineering, Architecture, Building Materials and Environment(caucong.com)
Abstract :
    Demand fluctuation is a major challenge in supply chain inventory management because it affects order quantity, safety stock, shortage risk, and total inventory cost. Traditional inventory models often use average demand, which may lead to unreliable decisions under uncertain market conditions. This study proposes a data-driven robust optimization approach to improve inventory decisions under demand uncertainty. Historical demand data are used to construct an uncertainty set, and a robust optimization model is developed to determine optimal order quantities and safety stock levels while minimizing holding and shortage costs. The proposed model is compared with a deterministic inventory model over a 12-period planning horizon. The results show that the robust model eliminated shortages, improved the service level from 96.54% to 100%, and reduced total inventory cost from 2,384 to 1,824, equal to a 23.49% cost reduction.

Keywords : supply chain management inventory management demand fluctuation data driven robust optimization safety stock