Predicting Supplier Delivery Quality with Machine Learning

Supplier disruptions are often visible in operational data before they become obvious to planners, but turning those signals into a useful decision tool requires more than training a model.

For my master’s thesis, I translated stakeholder needs from cross-functional workshops into a supplier-risk use case, analyzed data from an industrial data lake and developed an end-to-end Python and machine-learning solution. I also built a web dashboard to make the results accessible for management and supplier-management workflows.

The solution identified approximately 25% of subsequent supplier risks up to five days in advance. Because the work used client data, the public case study focuses on the problem structure, system logic and decision process rather than confidential data or model details.