Google Cloud Professional Machine Learning Engineer — Question 93

You work for an online publisher that delivers news articles to over 50 million readers. You have built an AI model that recommends content for the company’s weekly newsletter. A recommendation is considered successful if the article is opened within two days of the newsletter’s published date and the user remains on the page for at least one minute.

All the information needed to compute the success metric is available in BigQuery and is updated hourly. The model is trained on eight weeks of data, on average its performance degrades below the acceptable baseline after five weeks, and training time is 12 hours. You want to ensure that the model’s performance is above the acceptable baseline while minimizing cost. How should you monitor the model to determine when retraining is necessary?

Answer options

• A. Use Vertex AI Model Monitoring to detect skew of the input features with a sample rate of 100% and a monitoring frequency of two days.
• B. Schedule a cron job in Cloud Tasks to retrain the model every week before the newsletter is created.
• C. Schedule a weekly query in BigQuery to compute the success metric.
• D. Schedule a daily Dataflow job in Cloud Composer to compute the success metric.

Correct answer: C

Explanation

Option C is correct because calculating the success metric weekly allows you to monitor the model's performance against the acceptable baseline effectively. Options A and D focus on monitoring input features rather than the actual performance metric, and option B involves retraining the model without assessing its current effectiveness, which may not be cost-efficient.