A Hybrid Fuzzy Optimization Model for Cost-Effective and Sustainable Inventory Systems

Increasingly complex supply chains, caused by Uncertain Demand Patterns, Uncertain Suppliers, volatilities in the lead time to a supply buyer, and increasing pressure to become Sustainable, force exposure to increasing vulnerability for the stockholder to catch-up in inventory management, require a switch in the use of classical inventory models to account for these complexities. Classical inventory models were developed from a deterministic or probabilistic assumption, where a large portion of inventory management would have traditionally been conducted based on historical analysis of known demand. However, in reality, the data has an element of uncertainty due to significant ambiguity and a vast array of demand factors. This research introduces a new approach by combining elements of fuzzy-set theory with multiple objectives for optimizing inventory sustainably in the presence of uncertainty. Specifically, the new framework regarded as the hybrid fuzzy-optimization model incorporates components of economic costs, carbon emissions measures, fuzzy demand modeling, and an optimization component using hybrid GA (Genetic Algorithm) with a local search feature. A numerical case study analysis of a real-life scenario was conducted to confirm the model's performance, and sensitivity analyses illustrated how combining fuzzy uncertainty with Sustainable inventory management goals can affect a company's inventory decision. The findings of this investigation suggest that Hybrid Models outperform crisp only; fuzzy-optimally; and traditional inventory optimization where cost, service levels, and emission metrics are used for the three measures. The findings of this study present a comprehensive robust, and versatile decision-support system (DSS) that is applicable to modern-day Supply Chain Management that is characterized by High Uncertainty.