Trust, Risk & Safety intermediate

Model Drift

Also called: concept drift, data drift

Silent degradation as the world moves away from the data a model was trained on.

Drift happens because reality changes: customer behaviour shifts, vocabulary shifts, a competitor launches. The model is unchanged, but its accuracy quietly decays. The danger is that it fails without erroring, so only monitoring catches it.

In practice: A demand forecast trained pre-inflation that keeps returning confident, wrong numbers.