PROFESSIONAL-MACHINE-LEARNING-ENGINEER Question #234: Real Exam Question with Answer & Explanation

Question

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?

Options

• ADownload the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI
• BDownload the weather and flu data each month. Configure Cloud Scheduler to execute a Vertex
• CDownload the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI
• DDownload the weather data each week, and download the flu data each month. Deploy the model

Explanation

To minimize cost for a BigQuery ML model predicting monthly flu infections using weekly weather data and monthly flu statistics, configure monthly retraining.

Common mistakes.

• A. Retraining weekly would incur higher costs without providing a clear benefit for a model predicting monthly flu infections, as the primary target variable only updates monthly.
• B. Downloading weather data only monthly might result in less fresh feature data if weekly trends are valuable, and executing a Vertex AI custom job might be more complex than a direct BigQuery ML CREATE OR REPLACE MODEL for a BQML model.
• C. Retraining weekly with all data, including monthly flu data, is not cost-optimal because the target variable for prediction only changes monthly.

Concept tested. Model retraining policy optimization

Reference. https://cloud.google.com/bigquery-ml/docs/model-management#update_or_retrain_your_model

No community discussion yet for this question.