AI engineering glossary · MLOps, LLMOps cloud
What is model validation?
Model validation: Checks run on a candidate model before release: accuracy against a baseline, performance on important slices of data, robustness, latency, fairness and format correctness. A candidate that fails a threshold is blocked from promotion.
Model validation: an example
A pipeline rejects a new model whose recall for rural users is 9 points lower than for urban users, even though overall accuracy improved.
Related terms
- Model promotion
- Regression test
- Model registry
- Data validation
More MLOps, LLMOps cloud terms
- Model versioning
- Monitoring
- Multi-stage build
- Observability
- On-call
- OpenTelemetry
- Population stability index
- Postmortem
Where you learn it
Model validation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.