Evaluation
Model Drift
When a deployed AI model's accuracy quietly degrades over time because the real world has changed since it was trained.
Definition
The degradation of a model's predictive performance over time due to changes in the underlying data distribution or relationships. Includes concept drift (changing relationships) and data drift (changing inputs).
Why it matters
A model that was 95% accurate at launch can silently drop to 70%, continuous monitoring is non-negotiable.
Where Sophizo applies this
Sophizo deploys Model Drift inside revenue and AI engagements with growth-stage operators and PE-backed portfolios.
See ForecastIQ →Related terms in Evaluation
Agent Evals
Standardized tests for AI agents to prove they are smart, safe, and reliable before they are deployed.
AI Model Monitoring
Keeping a constant watch on a deployed AI to make sure it hasn't gotten broken or less accurate over time.
Area Under the Curve (AUC)
A score from 0 to 1 that tells you how good your model is at distinguishing between two things (like spam vs. not spam).
Conformal Prediction
A technique that tells you not just what the AI predicts, but how confident it is, with a mathematical guarantee.
From vocabulary to outcomes
Ready to put Model Drift to work?
Knowing the term is step one. Deploying it inside a revenue architecture that compounds is what Sophizo builds.
Book a Discovery Call