Answer-first summary for fast verification
Answer: 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.
The correct answer is D. This approach minimizes costs by downloading weather data weekly to capture potential changes while downloading flu data only when it is updated monthly. Using Vertex AI's feature drift monitoring allows retraining the model only when significant changes in the data distribution are detected, ensuring the model remains accurate without unnecessary retraining cycles and additional processing costs.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You work for a pharmaceutical company based in Canada that has developed a BigQuery ML model to predict the number of flu infections for the upcoming month across the country. This model uses various data inputs, such as weather data published weekly and flu infection statistics published monthly. With the goal of minimizing costs while maintaining the model's accuracy, you need to configure a model retraining policy. What should you do?
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.
No comments yet.