AI engineering glossary · ML fundamentals
What is covariate shift?
Covariate shift: A kind of distribution shift where the distribution of the input features changes between training and use, while the rule linking inputs to outputs stays the same. The model may be asked about regions of input space it saw rarely, so errors rise.
Covariate shift: an example
A credit model trained mainly on salaried urban applicants starts receiving many rural self-employed applicants.
Related terms
More ML fundamentals terms
- Cross-validation
- Curse of dimensionality
- Data leakage
- Data snooping
- Data-centric AI
- Dataset
- Decision threshold
- Discriminative model
Where you learn it
Covariate shift is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.