Adaptive Inventory Optimization for Social Media- Driven Demand Using Heptagonal Fuzzy EOQ and AI Forecasting

This paper presents a hybrid inventory optimization model designed for markets influenced by rapid social-media
trends. The approach integrates the fuzzy Economic Order Quantity (EOQ) framework with Heptagonal Fuzzy
Numbers (HFNs) to capture uncertainty in demand and costs, while Artificial Intelligence (AI) techniques are
employed to forecast demand surges in real time. A case study on Matcha tea, a globally trending product,
illustrates the effectiveness of the model. The results show that the fuzzy-AI framework provides more reliable
stock recommendations than the classical EOQ model, particularly under volatile conditions. By combining
uncertainty modeling with predictive analytics, the proposed method offers a practical decision-support tool for
businesses facing unpredictable, trend-driven markets.
Keywords: Fuzzy EOQ, Heptagonal fuzzy number, Artificial intelligence, Inventory optimization, Social media