Google Cloud Professional Machine Learning Engineer — Question 125

You have successfully deployed to production a large and complex TensorFlow model trained on tabular data. You want to predict the lifetime value (LTV) field for each subscription stored in the BigQuery table named subscription. subscriptionPurchase in the project named my-fortune500-company-project.

You have organized all your training code, from preprocessing data from the BigQuery table up to deploying the validated model to the Vertex AI endpoint, into a TensorFlow Extended (TFX) pipeline. You want to prevent prediction drift, i.e., a situation when a feature data distribution in production changes significantly over time. What should you do?

Answer options

• A. Implement continuous retraining of the model daily using Vertex AI Pipelines.
• B. Add a model monitoring job where 10% of incoming predictions are sampled 24 hours.
• C. Add a model monitoring job where 90% of incoming predictions are sampled 24 hours.
• D. Add a model monitoring job where 10% of incoming predictions are sampled every hour.

Correct answer: B

Explanation

The correct answer is B because monitoring 10% of incoming predictions every 24 hours allows for effective tracking of prediction drift without overwhelming the system. Options A and D suggest continuous retraining or more frequent sampling, which might be excessive for monitoring purposes. Option C over-samples at 90%, which could lead to unnecessary resource consumption without significantly improving drift detection.