About

A longer version of who I am and what I'm working on.

Sylvain Estebe

Background

I'm interested in how agents translate information about their environment into behavior — whether the agent is a person, a group, or a population. I like moving between scales, building models that are simple enough to reason about and testable against data.

In practice, I build Bayesian cognitive models and agent-based simulations, or do applied data science: customer segmentation and churn modeling at Norlys, LLM annotation pipelines. Earlier, at RITMO in Oslo, I worked on the experimental side — motion capture, eye-tracking, and physiological recording to measure cognitive and physical effort in listeners and pianists.

I also care about design and presentation — a sensibility carried over from a decade as a music producer before academia, composing for Jok'air and Disiz, with work for ads and theatre (four gold records, one platinum).

Based in Aarhus, Denmark. Ongoing collaboration at Institut Jean Nicod (ENS/PSL, Paris).

The scenic route

I did not take the straight path. Roughly, in order:

Industry

Data science intern at Norlys (Danish energy provider). Customer segmentation from high-dimensional data using clustering and UMAP.

Teaching & outreach

Contact

Open to research collaborations and short-term consulting on Bayesian modeling, LLM pipelines, and behavioral data.

sylvain.estebe@gmail.com · GitHub · ORCID · LinkedIn · Bluesky · Instagram

CV (PDF)