AWS Certified Machine Learning – SpecialtyMachine Learning Implementation and OperationsEasy
A data science team has developed a new machine learning model to predict customer churn. They need to deploy this model to production in a way that minimizes downtime and allows for a quick rollback if issues arise, while also being able to gradually shift traffic to the new model. Which deployment strategy should they use?
- ACanary Deployment
- BShadow Deployment
- CBlue/Green Deployment
- DA/B Testing
Show answer & explanationAnswer & explanation
Correct answer: A. Canary Deployment
Canary deployment allows for a gradual rollout of a new model version to a small subset of users, monitoring its performance, and then progressively increasing traffic. This minimizes risk and enables quick rollback if issues are detected, aligning with the team's requirements.
Why the other options are wrong
- B. Shadow deployment sends production traffic to a new model for evaluation without impacting live users, but does not serve predictions to users.
- C. Blue/Green deployment switches all traffic at once, which does not allow for gradual traffic shifting.
- D. A/B testing is used for comparing model performance over time with different user groups, not primarily for risk-averse deployment of a single new model version.
Canary Deployment
A deployment strategy where a new version of a model is rolled out to a small subset of users first, monitored for performance, and then gradually rolled out to more users if successful.
- Minimizes risk of new deployments.
- Allows for quick rollback.
- Enables real-world performance monitoring before full rollout.
Memory trick: Canary sings a little, then a lot.