You have deployed multiple model versions from Vertex AI Model Registry and want to conduct A/B testing to determine the best performing model with the simplest approach. What should you do?

Exam-Like

Split incoming traffic to distribute prediction requests among the versions. Monitor the performance of each version using Vertex AI's built-in monitoring tools.

100.0%

Split incoming traffic among Google Kubernetes Engine (GKE) clusters, and use Traffic Director to distribute prediction requests to different versions. Monitor the performance of each version using Cloud Monitoring.

0.0%

Split incoming traffic to distribute prediction requests among the versions. Monitor the performance of each version using Looker Studio dashboards that compare logged data for each version.

0.0%

Split incoming traffic among separate Cloud Run instances of deployed models. Monitor the performance of each version using Cloud Monitoring.

0.0%

Google Professional Machine Learning Engineer

Get started today

Comments

You have deployed multiple model versions from Vertex AI Model Registry and want to conduct A/B testing to determine the best performing model with the simplest approach. What should you do?