Google Cloud Professional Machine Learning Engineer — Question 193

You recently deployed a model to a Vertex AI endpoint. Your data drifts frequently, so you have enabled request-response logging and created a Vertex AI Model Monitoring job. You have observed that your model is receiving higher traffic than expected. You need to reduce the model monitoring cost while continuing to quickly detect drift. What should you do?

Answer options

• A. Replace the monitoring job with a DataFlow pipeline that uses TensorFlow Data Validation (TFDV)
• B. Replace the monitoring job with a custom SQL script to calculate statistics on the features and predictions in BigQuery
• C. Decrease the sample_rate parameter in the RandomSampleConfig of the monitoring job
• D. Increase the monitor_interval parameter in the ScheduleConfig of the monitoring job

Correct answer: C

Explanation

The correct answer is C because decreasing the sample_rate will reduce the number of samples collected for monitoring, thereby lowering costs while still allowing for drift detection. Option A is incorrect as it does not directly address the cost issue. Option B also fails to provide a cost-effective monitoring solution. Option D would actually increase monitoring frequency, which could lead to higher costs, contrary to the goal of reducing expenses.