Google Sample Question 12 of 15

You recently used Vertex AI Prediction to deploy a custom-trained model in production. The automated re-training pipeline made available a new model version that passed all unit and infrastructure tests. You want to define a rollout strategy for the new model version that guarantees an optimal user experience with zero downtime. What should you do?

Source: Google Cloud OFFICIAL

Official sample question published by Google Cloud. WiseOwlLearns is not affiliated with Google LLC.

All explanations and Option Analyzer™ content are generated by WiseOwlLearns and are not endorsed by Google Cloud.

A Release the new model version in the same Vertex AI endpoint. Use traffic splitting in Vertex AI Prediction to route a small random subset of requests to the new version and, if the new version is successful, gradually route the remaining traffic to it.
B Release the new model version in a new Vertex AI endpoint. Update the application to send all requests to both Vertex AI endpoints, and log the predictions from the new endpoint. If the new version is successful, route all traffic to the new application. ✓ Correct
C Deploy the current model version with an Istio resource in Google Kubernetes Engine, and route production traffic to it. Deploy the new model version, and use Istio to route a small random subset of traffic to it. If the new version is successful, gradually route the remaining traffic to it.
D Install Seldon Core and deploy an Istio resource in Google Kubernetes Engine. Deploy the current model version and the new model version using the multi-armed bandit algorithm in Seldon to dynamically route requests between the two versions before eventually routing all traffic over to the best-performing version.
🦉 Explanation by WiseOwl Tutor™ — not endorsed by Google

Shadow deployments minimize the risk of affecting user experience while ensuring zero downtime by executing predictions in parallel without returning them to users. Canary deployments (via traffic splitting or Istio) route a subset of actual user traffic to the new model version, which violates the requirement to guarantee an optimal user experience with zero risk of affecting the production user experience. Multi-armed bandits also expose users to the new version.

Ready to practice?

These 15 official sample questions are free to practice on WiseOwlLearns — no account required. Get real-time tutoring from WiseOwl Tutor™ and step-by-step elimination reasoning from Option Analyzer™.

Start Practicing Free View Professional Machine Learning Engineer Course →