Event details from: Business Analytics Seminar: Bram Biemans (Eindhoven University of Technology (TU/e))

Date
26 January 2026
Time
12:00 – 13:00

Abstract:

Modern supply chain planning relies heavily on large-scale optimization models. Despite their numerous practical and economic benefits, human planners often doubt the solutions provided by automated optimizers, which limits their potential effectiveness. While explainability has been widely studied in machine learning, only limited work exists for optimization-based decision problems, and existing approaches are often problem-specific or require repeated, time-consuming re-solving, making them impractical for large-scale supply chain settings.

In this talk, I present a position on the need for explanation methods that are fast, generalizable, and human-centered, enabling planners to understand why specific planning decisions were made by the optimization model and how they compare to plausible alternatives. I discuss key research challenges and outline a research agenda for developing explanation frameworks that deliver contrastive, user-friendly feedback while remaining faithful to the underlying optimization logic. The ultimate goal is to advance explanation systems that support meaningful human–machine collaboration in supply chain optimization.

General information:

This seminar will be organised in a hybrid setup. If you are interested in joining this seminar, please send an email to the secretariat of Amsterdam Business School at secbs-abs@uva.nl.