Smart EOQ Models: Incorporating AI and Machine Learning for Inventory Optimization

Abstract

Traditional Economic Order Quantity EOQ models rely on static assumptions e g constant demand fixed holding cost failing in volatile environments This research advances dynamic inventory control through an AI-driven framework where 1 Demand Forecasting Machine learning LSTM GBRT estimates time-varying demand covariates like promotions seasonality residuals 2 Adaptive EOQ Optimization Reinforcement Learning RL dynamically solves the following optimization problem Subject to Where Order quantity at time Reorder point at time Holding cost per unit Backorder shortage cost per unit Fixed ordering cost Indicator function 1 if else 0 Inventory on hand positive part of Backordered inventory negative part of Demand at time Validation was performed using sector-specific case studies Pharma Perishability constraint shelf-life reduced waste by 27 3 Retail Promotion-driven demand volatility 58 mitigated cutting stockouts by 34 8 Automotive RL optimized multi-echelo n coordination reducing shortage costs by 31 5 The framework reduced total costs by 24 9 versus stochastic EOQ benchmarks Key innovation closed-loop control where RL adapts to real-time supply-chain states