OPTIMIZATION OF MULTI-ITEM INVENTORY SYSTEMS UNDER UNCERTAINTY: A PROBABILISTIC APPROACH

This paper addresses the optimization of multi-item inventory systems under unpredictability , utilizing a probabilistic approach to account for fluctuating demand and supply. The primary goal is to create a robust Model of Inventory that optimizes order quantities and reorder points across multiple items, while minimizing total costs such as holding, shortage, and setup costs. The model incorporates stochastic variables, including demand distributions and lead times, to reflect real-world uncertainties. By applying probabilistic optimization techniques and leveraging dynamic programming, the study evaluates different inventory policies and assesses their effectiveness under various uncertainty scenarios. The results demonstrate the model's capacity to improve inventory performance, reduce costs, and balance trade-offs between service levels and stockouts. Additionally, sensitivity analyses are conducted to understand the influence of key parameters such as demand variability, storage constraints, and risk preferences on optimal solutions, providing valuable insights for decision-makers in supply chain management.