How to configure Vertex AI Model Monitoring for high volume?

You developed a custom model by using Vertex AI to forecast the sales of your company’s products based on historical transactional data. You anticipate changes in the feature distributions and the correlations between the features in the near future. You also expect to receive a large volume of prediction requests. You plan to use Vertex AI Model Monitoring for drift detection and you want to minimize the cost. What should you do?

  1. Use the features for monitoring. Set a monitoring-frequency value that is higher than the default.
  2. Use the features for monitoring. Set a prediction-sampling-rate value that is closer to 1 than 0.
  3. Use the features and the feature attributions for monitoring. Set a monitoring-frequency value that is lower than the default.
  4. Use the features and the feature attributions for monitoring. Set a prediction-sampling-rate value that is closer to 0 than 1. Source Reference Answer

Community Votes

D
100%

100% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

This tests cost optimization in Vertex AI Model Monitoring, specifically balancing the need for detailed drift detection (attributions) against the high costs of sampling large volumes of prediction requests.

To minimize Vertex AI Model Monitoring costs for high-volume prediction requests, enable feature attribution monitoring and set the prediction sampling rate closer to 0. The community consensus confirms that lowering the sampling rate is the most effective cost-control measure for high-traffic models.

Selecting options with higher monitoring frequencies or sampling rates (Options A or B) is a common mistake because these settings directly increase costs, contradicting the requirement to minimize expenditure.

Community Discussion (4 comments)

fitri001 👍 3 Selected: D
Feature and Feature Attribution Monitoring: Since you anticipate changes in feature distributions and correlations, monitoring both features and their attributions provides a more comprehensive view of potential drift. Feature attributions explain how each feature contributes to the model's predictions. Monitoring them helps identify if these contributions are changing as expected. Lower Prediction Sampling Rate: This reduces the cost associated with Vertex AI Model Monitoring. The sampling rate determines the percentage of prediction requests used for monitoring calculations. A lower rate reduces the number of predictions analyzed, lowering monitoring costs. However, it's important to strike a balance between cost and having enough data for drift detection.
BlehMaks 👍 3 Selected: D
if we expect a large volume of prediction requests then pick D. if we expect the changes to be infrequent then C https://cloud.google.com/vertex-ai/docs/model-monitoring/overview#considerations
pikachu007 👍 2 Selected: D
Given the need to minimize costs while addressing changes in feature distributions and correlations, option D - "Use the features and the feature attributions for monitoring. Set a prediction-sampling-rate value that is closer to 0 than 1" seems to be a reasonable choice. This option allows monitoring both features and feature attributions, offering insights into changes in feature importance, while the lower prediction-sampling-rate helps manage costs by monitoring a subset of predictions. It's a trade-off between cost efficiency and the need for effective drift detection
b1a8fae 👍 2 Selected: D
Not A. because higher monitoring frequency, higher cost. Not B. because higher prediction request sample rate, higher cost. Between the remaining 2, better to lower the prediction request sample rate so only a small fraction of the latest data is evaluated for drift, also because lots of data are expected so a small perecentage should suffice to detect drift.

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

Option D is correct because it addresses the need to detect changes in feature correlations—requiring feature attributions—while managing costs for high traffic. Setting the prediction-sampling-rate closer to 0 ensures that only a small fraction of the large request volume is analyzed, which is the primary lever for reducing monitoring expenses.

Why the Other Options Are Wrong

Options A and B are incorrect because increasing the monitoring frequency or sampling rate directly increases costs, violating the requirement to minimize them. Option C lowers the frequency but does not mitigate the cost impact of a large volume of requests as effectively as lowering the sampling rate does.

Community Comment Notes

Community members highlighted that with a large volume of prediction requests, reducing the sampling rate is crucial to keep costs manageable. Additionally, comments noted that since the question mentions anticipating changes in correlations between features, monitoring feature attributions is necessary to detect these specific shifts.

Official Reference

https://cloud.google.com/vertex-ai/docs/model-monitoring/overview#considerations

Exam Strategy

When asked to minimize costs for high-traffic models, prioritize reducing the prediction sampling rate over changing the monitoring frequency. Remember that feature attributions are specifically required to detect changes in feature correlations, distinguishing them from simple distribution shifts.

Related Analysis

You need to deploy a scikit-leam classification model to pro

S-Grade

You developed a Python module by using Keras to train a regr

S-Grade

You are deploying a new version of a model to a production V

S-Grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide