Manufacturing companies lack visibility of the procurement interdependencies between the suppliers within their supply network. However, knowledge of these interdependencies is useful to plan for operational disruptions, as well as tracking wider risk in the supply chain ecosystem, which may range from identifying suppliers that engage in unethical and unsustainable practices.
The supply Chain AI Lab leads a number of activities Supply Network Reconstruction and Link Prediction, in order to increase visibility of supply networks, which in turn enables us to create strategies for improved resilience, and sustainability.
These include the VIPr project, where we developed the Supply Chain Miner, a Natural Language Processing approach that emables the extraction and prediction of company to company relationships from the World Wide Web. As part of VIPr we have also developed the Supply Network Link Predictor (SNLP) to infer supplier interdependencies using the manufacturer’s incomplete knowledge of the network. SNLP uses topological data to extract relational features from the known network to train a classifier for predicting potential links.
In ChainedRisk, we created multiple approaches that predict supplier links using Graph Neural Networks and Knowledge Graphs. Each of these approaches build on public and private datasets, giving rise to exciting tools that make automated supply chain mapping possible.
Researcher: Edward Kosasih, Ajmal Aziz, Nils Brockmann, Phillip Schaffer