← 🔁 MLOps & Lifecycle

Core

Feature Store: Online vs Offline and Training-Serving Skew

One feature definition materialized to an offline store for training and an online store for serving. The fix for training-serving skew and leakage.

a free account unlocks the core curriculum tier · no card

COURSES COVERING THIS TOPIC

No lesson covers this one directly yet. These teach the surrounding topic from the beginning.

Applied AI Engineering·The interviewPremium12mTurning this course into a study planA concrete four-week plan mapping the seven modules onto the question bank, plus what to do differently if your interview is next week rather than next month.

RELATED CONCEPTS

Drift Detection Model Monitoring in Production CI/CD for Models Cross-Validation (Done Right)

PRACTICE THIS IN REAL QUESTIONS

MLOps & ML EngineeringWhat is a feature store, and how does it prevent training-serving skew?→MLOps & ML EngineeringYour model scores well offline but worse online, and you suspect training-serving skew. How do you find it?→System Design for AI in ProductionDesign a real-time feature pipeline / feature store for online ML.→MLOps & ML EngineeringYour online features are stale, and predictions suffer for it. How do you guarantee feature freshness?→MLOps & ML EngineeringHow do you change or remove a feature without breaking the models that depend on it?→System Design for AI in ProductionYour model looks great offline but drops CTR 2% in production. How do you ship safely and find the cause?→

COMPANIES THAT ASSUME THIS

NVIDIA C3 AI AWS Databricks Cohere Perplexity