Welcome

Hi, I’m Dr. Barrie Kersbergen.

I work on complex, cross-organizational problems in large-scale e-commerce, particularly where the problem itself, the right abstraction, or the technical direction is not yet clear. My work often involves bringing together perspectives across teams and disciplines, challenging assumptions, developing new approaches, and setting technical direction that can be translated into practice and used by others.

A major focus of my current work is decision-making under uncertainty: moving from predicting what will happen to deciding what to do when the future is uncertain. This includes probabilistic forecasting, uncertainty quantification and calibration, scenario-based planning, and methods that connect predictions to operational decisions.

My work combines technical leadership, machine learning, decision science, and applied research.

My academic work has focused primarily on recommender systems and machine learning for e-commerce. My PhD research investigated scalable session-based recommendation under real-world constraints such as massive product catalogs, billions of interactions, sparse behavioral data, strict latency requirements, and data quality issues.

In my PhD thesis, Expanding Boundaries in Scalable Session-Based Recommendations, I show that well-designed nearest-neighbor algorithms can rival or outperform deep learning approaches on large-scale recommendation tasks, particularly when computational and production constraints are taken into account. The work also covers resource-aware benchmarking and scalable data debugging and attribution using Shapley values.

Across these areas, I am particularly interested in methods that are not only technically strong, but also scalable, uncertainty-aware, and useful for real-world decisions.

This website contains my publications, research, teaching, and other academic and professional work.