Scholarlink

<p>The increasing complexity and globalization of modern supply chains have amplified exposure to multi-faceted risks, ranging from operational disruptions to systemic failures. Traditional risk management strategies, which are often based on static models, heuristic approaches, expert judgment, and limited real-time data, have struggled to offer the agility and foresight required in today’s volatile environments. In recent years, deep learning (DL), a subfield of artificial intelligence (AI), has emerged as a transformative tool for supply chain risk management (SCRM), enabling data-driven, adaptive, and scalable solutions across the entire risk management lifecycle. Guided by four research questions addressing risk classification, architectural alignment, lifecycle effectiveness, and adoption barriers, this review synthesizes the recent literature on the application of DL techniques to four key stages of SCRM: risk identification, assessment, mitigation, and monitoring. By analyzing empirical studies, model architectures, and real-world applications, the paper highlights how DL enables predictive insights, real-time disruption detection, and proactive decision-making. A dynamic risk classification framework is introduced to better capture the evolving nature of supply chain threats. The review concludes by identifying critical challenges and future research directions, emphasizing the potential of DL to redefine resilience and strategic agility in supply chains.</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

A Systematic Review on Applications of Deep Learning in Supply Chain Risk Management

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Roop Harshit Vankayalapati,
  • Amarnath Banerjee

摘要

The increasing complexity and globalization of modern supply chains have amplified exposure to multi-faceted risks, ranging from operational disruptions to systemic failures. Traditional risk management strategies, which are often based on static models, heuristic approaches, expert judgment, and limited real-time data, have struggled to offer the agility and foresight required in today’s volatile environments. In recent years, deep learning (DL), a subfield of artificial intelligence (AI), has emerged as a transformative tool for supply chain risk management (SCRM), enabling data-driven, adaptive, and scalable solutions across the entire risk management lifecycle. Guided by four research questions addressing risk classification, architectural alignment, lifecycle effectiveness, and adoption barriers, this review synthesizes the recent literature on the application of DL techniques to four key stages of SCRM: risk identification, assessment, mitigation, and monitoring. By analyzing empirical studies, model architectures, and real-world applications, the paper highlights how DL enables predictive insights, real-time disruption detection, and proactive decision-making. A dynamic risk classification framework is introduced to better capture the evolving nature of supply chain threats. The review concludes by identifying critical challenges and future research directions, emphasizing the potential of DL to redefine resilience and strategic agility in supply chains.