INVENTORY CONTROL MODELS: DETERMINISTIC AND PROBABILISTI MODELS

Abstract

Inventory comprises finished goods, raw materials, and product stock that a company holds for sale. It is a crucial asset for manufacturing firms, directly impacting cost control, decision-making, and profitabil-ity. When managed effectively, inventory can drive significant profits, but poor management can lead to substantial losses. Inventory control is a critical aspect of operations management, ensuring that the right quantity of stock is maintained to meet customer demands while minimizing costs. This thesis explores two primary categories of inventory control models: deterministic and probabilistic. Deterministic models operate under the assumption that all variables such as demand, lead time, and order quantities are known with certainty. These models are particularly useful in stable environments and provide a foundation for understanding basic inventory principles. In contrast, probabilistic models account for uncertainty and variability in demand and lead times, offering more realistic solutions in dynamic and uncertain environ-ments. The study begins with a detailed review of the Economic Order Quantity (EOQ) model and its vari-ations. It then transitions to probabilistic models, emphasizing safety stock calculations, service level optimization, and stochastic demand forecasting. A comparative analysis highlights the strengths and limitations of each approach, supported by numerical examples and case studies. The Deterministic In-ventory Model assumes a known and fixed demand, making it a widely used method for inventory control. In contrast, the Probabilistic Inventory Model accounts for uncertainties and variability in demand, lead time, and other factors. The proposed methodology aims to optimize costs associated with holding inven-tory, ordering stock, and maintaining safety stock. This study provides an in-depth exploration of these models and their applications across industries. To reinforce the practical applicability of these models, two case studies-one for each model type-have been included, demonstrating their implementation in real-world scenarios. Through mathematical modeling, simulation, and real-world applications, this research aims to pro-vide a comprehensive understanding of inventory control strategies. The thesis concludes with insights on model selection based on business environment characteristics, recommending hybrid approaches for enhanced decision-making in complex supply chains.