Operations research model for inventory optimization through statistical demand analysis and linear programming

Abstract

Efficient inventory management requires integrating demand uncertainty, costs, and replenishment decisions within a quantitative framework. This research develops an Operations Research model for inventory optimization by integrating statistical analysis, demand forecasting, ABC classification, Economic Order Quantity [EOQ], Safety Stock [SS], Reorder Point [ROP], and Mixed-Integer Linear Programming [MILP]. The procedure uses historical data to estimate demand parameters and establish differentiated replenishment policies. These parameters are subsequently incorporated into the mathematical model to determine order quantities and periods while minimizing relevant inventory costs. The results reveal a significant economic concentration among priority items and an approximate 46% reduction in relevant inventory costs compared with the baseline policy. Sensitivity analysis confirms the stability of the proposed model under the evaluated variations in demand, holding costs, and safety stock. Overall, the integrated framework provides a reproducible quantitative approach for connecting predictive analysis with prescriptive optimization and supporting cost-efficient inventory and logistical decision-making.