It Works as an ML Notebook : So Why Does It Fail in Production? FOSSASIA Summit 2026

FOSSASIA Summit 2026 Sunday, 8 March, 2026 9:00 AM (Asia/Bangkok) To Tuesday, 10 March, 2026 7:30 PM (Asia/Bangkok)

Info Featured Schedule Speakers Exhibition

It Works as an ML Notebook : So Why Does It Fail in Production?Data science notebooks often represent a "perfect analysis”. But the problem lies in turning them into actual working services in production environments. In this proposed workshop session, these are lessons learned working as an ML Engineer/ Data Scientist at Air Arabia, bridging data science work that looks perfect in notebooks with how those ML systems need to be optimized to be in production. Using a problem in Formula 1 as an example participants will see, <ul><li> How refactoring of a Jupyter notebook into a production-ready Python service happens using best practices,</li><li>Deploy it as a scheduled job or inference API (FastAPI vs Cron), </li><li>Observability to catch failures. (Grafana, logging)</li><li>Post-deployment maintenance</li></ul> Also, exploration will be done on how real-world business behavior (Changing records, data inconsistencies, data drift) can invalidate predictions even when models are technically correct, and how explainability plays a role for stakeholders.