AI engineering glossary · MLOps, LLMOps cloud
What is model monitoring?
Model monitoring: Tracking a deployed model's behaviour over time: input data quality, prediction distributions, latency, errors and, where labels arrive, accuracy. It reveals when the world has changed or the model has stopped working well.
Model monitoring: an example
A dashboard flags that the share of loan applicants under 25 doubled this month and that approval scores have shifted.
Related terms
- Data drift
- Concept drift
- Model performance decay
- Observability
More MLOps, LLMOps cloud terms
- Model promotion
- Model registry
- Model validation
- Model versioning
- Monitoring
- Multi-stage build
- Observability
- On-call
Where you learn it
Model monitoring is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.