Generative Artificial Intelligence in Supply Chain: Review, Trends, and Future Directions

Abstract

Background: Generative artificial intelligence (GenAI) has attracted significant attention in supply chain management (SCM) due to its potential to improve data-driven decision-making and operational performance. However, existing studies mainly focus on individual GenAI models or specific supply chain applications, lacking a comprehensive understanding of how different GenAI architectures support decision-making across the supply chain. Methods: This study conducts a systematic literature review using the PRISMA framework to examine the applications of Generative Adversarial Networks (GANs), Transformers, Variational Autoencoders (VAEs), and flow-based models within a six-level supply chain decision-making framework. A total of 692 peer-reviewed publications were analyzed using bibliometric methods, including keyword co-occurrence, temporal and density analyses, and Supervised Embedding Visualization. Results: Current research is concentrated on Transformer and GAN applications, particularly in data analytics, optimization, forecasting, manufacturing, transportation, logistics, and quality management. The analyses also reveal major research themes, the evolution of GenAI in SCM, and limited attention to sustainability, cybersecurity, resilience, and reverse logistics. Conclusions: This study provides a comprehensive overview of GenAI applications in SCM, identifies key research gaps, and offers a foundation for future research while helping practitioners evaluate opportunities and limitations of GenAI for supply chain decision-making.