DisneySystem DesignMembers
Safe Model Rollout and Feature-Cost Reduction for ML Serving
Members only
A two-part ML-systems discussion. One part is about gaining confidence in a new production model without putting business metrics at risk and then proving its impact. The other is about shrinking the serving cost of a model with a very large feature set while keeping quality.
MLE
DS
system-design
ml-infra
ab-testing
experiment-design
inference
caching
feature-engineering
Frequency
Single report
Last asked
—
Stage
onsite-system-design
Members get
- Full problem statement
- 3 progressive hints
- Step-by-step approach
- Full solution with code
- 7 talking points
- 5 follow-up questions with answer directions
- Preparation drills
Log in to continue reading the full content
Comments
Sign in to join the discussion
Loading...
