Smart and Secure Supply Chains in the New Era Using Artificial Intelligence

Author:

Akbar Demiral1,ŞİMŞEK Murat1

Affiliation:

1. OSTİM Technical University

Abstract

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.

Publisher

Springer Science and Business Media LLC

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3