Gurgen Hovakimyan - Beyond Static Models: Detection and Interpretability of Concept Drift

Gurgen Hovakimyan, Staff R&D Engineer at Synopsys, presents a talk on
“Beyond Static Models: Advancing the Detection and Interpretability of Concept Drift.”

In real-world machine learning systems, data is rarely static - it evolves, shifts, and drifts over time. This talk explores how concept drift can silently undermine model performance and how to build systems that not only detect these changes but also adapt in real time.

In this session, Gurgen dives into:
🔹 The real-world challenges of maintaining ML model reliability
🔹 Methods for detecting and interpreting concept drift
🔹 Practical strategies for building adaptive learning systems

This talk was recorded during the PyData Yerevan June 2025 Meetup held on June 19, 2025, at the American University of Armenia (AUA).
--
www.pydata.org

PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and R.

PyData conferences aim to be accessible and community-driven, with novice to advanced level presentations. PyData tutorials and talks bring attendees the latest project features along with cutting-edge use cases.

00:11 Welcome!

Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: https://github.com/numfocus/YouTubeVideoTimestamps

Видео Gurgen Hovakimyan - Beyond Static Models: Detection and Interpretability of Concept Drift канала PyData