Supply Chain Link Prediction on an Uncertain Knowledge Graph
With manufacturing companies outsourcing to each other, multi- echelon supply chain networks emerge in which risks can propagate over multiple entities. Considerable structural and organizational barriers hamper obtaining the supply chain visibility that would be required for a company to monitor and mitigate these risks. Our work proposes to combine the automated extraction of supply chain relations from web data using NLP with augmenting the results using link prediction. For this, the first graph neural network based approach to model uncertainty in supply chain knowledge graph reasoning is shown. We illustrate our approach on a novel dataset and manage to improve the state-of- the-art performance by 60% in uncertainty link prediction. Generated confidence scores support real-world decision-making. This is a work-in-progress paper.