Model Drift
The gradual degradation of a machine learning model’s accuracy and predictive power over time as real-world data changes.
Model Drift (or Concept Drift) describes the phenomenon where the real-world data a model encounters in production begins to deviate from the historical data it was originally trained on.
As the environment changes - due to shifting market trends, changing consumer behavior, or new regulations - the model's predictions become increasingly inaccurate and unreliable.
Robust MLOps pipelines constantly monitor for model drift. When drift crosses a critical threshold, the system automatically triggers a retraining phase, utilizing fresh data pipelines secured by data mobilization efforts to update the model's understanding of the world.