Soft Computing Applications for Supply Chain Management: A Survey

Abstract

Modern supply chain management is dynamic and becoming more complicated, which creates major problems for efficiency, flexibility, and decision-making. In situations involving unpredictable, imprecise, or quickly shifting supply and demand, traditional optimization and analytical techniques might be inadequate. In consideration of these difficulties, this study investigates the use of soft computing methods as effective alternatives for simulating and resolving actual supply chain management issues. These methods include fuzzy logic, genetic algorithms, artificial neural networks, and swarm intelligence. These methods perform especially well for improving the supply chain in several areas, such as demand forecasting, inventory management, logistics network design, distribution planning, and supplier selection and assessment. Organizations may develop more adaptable, reliable, and economic decision-making processes by utilizing self-learning, approximate reasoning, and adaptive characteristics of soft computing techniques. Consequently, this makes supply chain systems more flexible, adaptable, and responsive overall in the face of uncertainty and competitiveness globally.