MLOps

Concept Drift

A change in P(Y|X) - the same inputs now imply a different outcome.

Why interviewers ask about it

The dangerous one, because input-drift dashboards stay green while the model is systematically wrong. Adversarial domains guarantee it by design.

A binned measure of distribution shift between a reference and current sample. <0.1 stable, 0.1–0.25 moderate, >0.25 significant.

This term is part of the free AI/ML Engineer interview preparation module - browse the full glossary for every definition.