Visualising Industry Network-based Supply Chain Risks for Informed Opportunity Management

Ming Zhao, Omar Khadeer Hussain

Keywords: Supply Chain Risk Management, Supply Chain Visualisation, Large Language Models

TL;DR: This paper presents an extension of the LARD-SC (LLMs for Automated Risk Detection in Supply Chains) framework to support not only reactive risk mitigation but also proactive opportunity identification across broader industry networks.

Abstract: This paper presents an extension of the LARD-SC (LLMs for Automated Risk Detection in Supply Chains) framework to support not only reactive risk mitigation but also proactive opportunity identification across broader industry networks. By integrating structured supplier data with real-time, unstructured information streams from news feeds, the LARD-SC framework applies GPT-4o to identify, categorise, and visualise risk signals to create a unified, dynamic risk landscape for focal companies to visualise their globally dispersed supply chains. We demonstrate LARD-SC’s capability using Apple as a case study, leveraging its supply chain data to visualise and classify risks impacting its supply chain. Beyond reducing risk exposure, we then demonstrate how the LARD-SC framework can be used by the focal company to create opportunity-driven foresight. This can be used to enable strategic planning and competitive advantage by anticipating disruptions and acting ahead of rivals.

Submission Number: 18