Abstract
Artificial Intelligence (AI) is expected to play a huge role in the digital industry revolution, 4.0 and beyond. Added challenges presented by pandemic conditions has increased the need for effective use of digital and optimization techniques for a sustainable supply chain, both from suppliers’ and buyers’ perspectives. Buyers need to maintain a healthy pool of suppliers that can sustain added stresses and risks at times of crises, and suppliers need to improve their presence and visibility of their capabilities. Both these requirements are often addressed with more effective use of technology, particularly AI-based techniques, once the digital infrastructure with the right data set is established. For optimized supply chain management, choosing a supplier based solely on cost may prove insufficient. Buyers now must play a more proactive role towards establishing a healthy and functional arsenal of suppliers. This often requires the use of procurement decisions that go beyond short-term cost optimization but that targets long term risk optimization. Towards this goal, one of the most prevalent approaches used for planning, optimizing and forecasting the supply chains is AI-based methods. Decision support systems or relevant mechanisms need to employ practical AI techniques to handle these complex decision processes. Genetic Algorithms (GA), one of the widely used AI techniques, provides the optimal solution by analyzing multiple criteria at the same time to make an effective and efficient selection in supplier selection. Incorporating multiple criteria such as price, delivery time, customs and taxes, the supplier company's production type, warranty policy, quality assurance tests is very important in the competitive market environment. Among these, the use of Large Language Models (LLMs) stands out for their ability to analyze vast amounts of unstructured data, enabling more effective and efficient supplier selection by considering multiple criteria such as price, delivery time, customs, taxes, production types, warranty policies, and quality assurance tests. This capability is vital in the competitive market environment, where choosing a supplier involves not just cost considerations but also long-term risk optimization. Thus, LLMs integrate seamlessly into decision support systems, providing optimal solutions that enhance both planning and forecasting in supply chain management. In this study, an analysis was carried out through text generation with Distilgpt2, a large language model, as an effective way for supplier selection. Supplier selection was carried out using this artificial intelligence approach, which was carried out with an end-to-end approach, and the selection was made both in time and effectively.