Answer-first summary for fast verification
Answer: Deploy the model to a Vertex AI endpoint, and configure the model for batch prediction. Schedule the batch prediction to run weekly.
The question requires deploying a PyTorch model for weekly customer churn prediction while minimizing maintenance effort. Option C is optimal because Vertex AI's batch prediction service is specifically designed for offline inference on large datasets, can be scheduled to run automatically each week, and requires minimal infrastructure management compared to other options. Vertex AI handles scaling, monitoring, and maintenance, reducing operational overhead. Option A involves deploying on Cloud Run, which requires managing the container and scaling for online predictions, increasing maintenance. Option B uses GKE, which requires significant cluster management and maintenance. Option D uses online prediction with scheduled queries, which is inefficient for batch processing and requires maintaining an always-on endpoint, increasing costs and maintenance compared to batch prediction.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are an AI engineer at a popular video streaming platform. You have built a PyTorch classification model to predict customer churn. The customer retention team plans to contact at-risk customers with personalized offers each week. You want to deploy this model while minimizing maintenance effort. What should you do?
A
Use Vertex AI’s prebuilt containers for prediction. Deploy the container on Cloud Run to generate online predictions.
B
Use Vertex AI’s prebuilt containers for prediction. Deploy the model on Google Kubernetes Engine (GKE), and configure the model for batch prediction.
C
Deploy the model to a Vertex AI endpoint, and configure the model for batch prediction. Schedule the batch prediction to run weekly.
D
Deploy the model to a Vertex AI endpoint, and configure the model for online prediction. Schedule a job to query this endpoint weekly.
No comments yet.