Scholarlink

<p>In today’s rapidly evolving commercial landscape, manufacturing enterprises face significant challenges in maintaining resilience amid disruptions such as pandemics, natural disasters, and geopolitical conflicts. To address these challenges, we introduce a novel GPT-based early detection tool designed for real-time supply chain risk assessment. This system integrates proprietary company data, including supply chain portfolios, with publicly available information, such as news articles, to estimate risk scores for respective supply chains, thereby enhancing decision-making processes. Leveraging advanced machine learning techniques–Generative Pretrained Transformers (GPT), zero-shot learning, and structured outputs–the tool operates locally to ensure data privacy and minimize information leakage. Utilizing the "news-please" crawler and the "Llama 3.1" GPT model, the system continuously monitors selected media sources, providing timely risk assessments. Our research demonstrates the tool’s potential to enhance proactive risk management in supply chains, validated through testing on both real and augmented datasets. By evaluating four exemplary supply chains, we characterize the tool’s capability to support decision-making in unpredictable global environments. The results indicate that, while the system occasionally exhibits oversensitivity, it consistently aids in identifying critical events that may impact supply chain operations. Future developments will focus on refining the tool’s accuracy and expanding its applications, particularly in monitoring regulatory changes.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-driven risk estimation: a GPT-based approach to news monitoring for manufacturing resilience

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月8日

查看全文
  • Adrian Jacob,
  • Anas Ben Achour,
  • Uwe Teicher

摘要

In today’s rapidly evolving commercial landscape, manufacturing enterprises face significant challenges in maintaining resilience amid disruptions such as pandemics, natural disasters, and geopolitical conflicts. To address these challenges, we introduce a novel GPT-based early detection tool designed for real-time supply chain risk assessment. This system integrates proprietary company data, including supply chain portfolios, with publicly available information, such as news articles, to estimate risk scores for respective supply chains, thereby enhancing decision-making processes. Leveraging advanced machine learning techniques–Generative Pretrained Transformers (GPT), zero-shot learning, and structured outputs–the tool operates locally to ensure data privacy and minimize information leakage. Utilizing the "news-please" crawler and the "Llama 3.1" GPT model, the system continuously monitors selected media sources, providing timely risk assessments. Our research demonstrates the tool’s potential to enhance proactive risk management in supply chains, validated through testing on both real and augmented datasets. By evaluating four exemplary supply chains, we characterize the tool’s capability to support decision-making in unpredictable global environments. The results indicate that, while the system occasionally exhibits oversensitivity, it consistently aids in identifying critical events that may impact supply chain operations. Future developments will focus on refining the tool’s accuracy and expanding its applications, particularly in monitoring regulatory changes.