Google Cloud Professional Machine Learning Engineer — Question 222

You work for a pharmaceutical company based in Canada. Your team developed a BigQuery ML model to predict the number of flu infections for the next month in Canada. Weather data is published weekly, and flu infection statistics are published monthly. You need to configure a model retraining policy that minimizes cost. What should you do?

Answer options

• A. Download the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model weekly.
• B. Download the weather and flu data each month. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model monthly.
• C. Download the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model every month.
• D. Download the weather data each week, and download the flu data each month. Deploy the model to a Vertex AI endpoint with feature drift monitoring, and retrain the model if a monitoring alert is detected.

Correct answer: D

Explanation

Option D is correct because it allows for continuous monitoring of the model's performance through feature drift detection, ensuring that the model is retrained only when necessary, thus minimizing costs. Options A and C suggest retraining the model too frequently, which could lead to unnecessary costs without significant benefits. Option B does not leverage the weekly weather data, which is critical for timely predictions.