How to Identify ML Drift Before You Have a Problem
From Safe and Sound AI by Fiddler AI
May 31, 2025 · 9 min · Episode 5
About this episode
This episode discusses the challenges of drift in machine learning models and offers practical detection methods and strategies for maintaining model accuracy.
In this episode of Safe and Sound AI, we dive into the challenge of drift in machine learning models. We break down the key differences between concept and data drift (including feature and label drift), explaining how each affects ML model performance over time. Learn practical detection methods using statistical tools, discover how to identify root causes, and explore strategies for maintaining model accuracy. Read the article by Fiddler AI and explore additional resources on how AI Observability can help build trust into LLMs and ML models.
Topics covered
- machine learning
- drift
- model performance
- statistical tools
- AI observability
Keywords
- ML drift
- concept drift
- data drift
- feature drift
- label drift
- model accuracy
- detection methods
Mentioned in this episode
Organizations: Fiddler AI
More episodes of Safe and Sound AI
- The Anatomy of Agentic Observability · October 28, 2025 · 16 min
- Agentic Observability: The AI Architect's Essential Blueprint · July 24, 2025 · 14 min
- Industry’s Fastest Guardrails Now Native to NVIDIA NeMo · April 2, 2025 · 10 min
- Introducing Fiddler Guardrails: The Fastest in the Industry · February 27, 2025 · 7 min
- Should you Observe ML Metrics or Inferences? · February 12, 2025 · 13 min
- Tracking Drift to Monitor LLM Performance · December 12, 2024 · 12 min
Explore listener stats, chart rankings, contacts and more on the Safe and Sound AI podcast page.