About

I'm Mohammad Behbahani, a data scientist moving into AI engineering. My PhD research at Utrecht University was data science: Hidden Markov Models for dynamic networks (code), where most of the work is finding out whether a model is actually right. I now build AI systems the same way: retrieval, agents and evaluation, measured before I trust them, and shared through Oploy.

Published work:

• A multi-objective open shop model for optimizing scheduling in automotive repair shops, Decision Analytics Journal, 2026 (note, code)
• An artificial neural network metamodel to solve semi-expensive simulation optimization problems, Journal of Industrial Engineering, 2025 (note, code)
• Single-replicate longitudinal data analysis in the presence of multiple instrumental measurement errors, Computers & Industrial Engineering, 2020

All of them are on Google Scholar.

This notebook is where I write down experiments after I have run them: what I tried, what it cost, and what went wrong.

Each note ends with a short How to repeat this section, so you can check a result instead of taking my word for it.

Numbers in a note are snapshots from the date it was written. Prices and services change, and I say so when I notice.

If something here is wrong or no longer works, email me at info@oploy.eu. My code is on GitHub, and I am on LinkedIn.

This site uses Google Analytics to count visits.