Enhancing Supply Chain Decision-Making with Large Language Models: A Comparative Study of Ai-Driven Optimization

This study explores the potential of Large Language Models (LLMs) in optimizing supply chain decision-making by comparing their performance with traditional machine learning models, including Random Forest (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and Deep Neural Networks (DNN). The evaluation focuses on four key supply chain tasks: demand forecasting, supplier selection, inventory management, and logistics optimization. Results indicate that LLMs significantly outperform traditional models, particularly in tasks involving both structured and unstructured data. The LLM achieved superior accuracy in demand forecasting, supplier selection, and logistics optimization, demonstrating its capability to analyze complex, multi-dimensional data from sources such as transactional records, supplier feedback, and market trends. Although the LLM required more computational resources, its overall performance highlighted its potential to revolutionize supply chain management. The findings suggest that LLMs offer a promising approach to optimizing supply chain decisions, improving efficiency, reducing costs, and enhancing overall decision-making accuracy. Future research should focus on addressing the computational challenges and exploring broader applications of LLMs in supply chain contexts.