nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #147

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…

The correct answer is C. Schedule a weekly query in BigQuery to compute the success metric. The key constraints are: the model degrades after ~5 weeks, training takes 12 hours, and the success metric is already computable in BigQuery (updated hourly). A weekly BigQuery scheduled query directly measures the actual business success metric at low cost, giving enough lead…

Submitted by yuriko_h· Apr 18, 2026Monitoring, optimizing, and maintaining ML solutions

Question

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?

Options

  • AUse Vertex AI Model Monitoring to detect skew of the input features with a sample rate of 100%
  • BSchedule a cron job in Cloud Tasks to retrain the model every week before the newsletter is
  • CSchedule a weekly query in BigQuery to compute the success metric.
  • DSchedule a daily Dataflow job in Cloud Composer to compute the success metric.

How the community answered

(25 responses)
  • A
    16% (4)
  • B
    8% (2)
  • C
    72% (18)
  • D
    4% (1)

Explanation

The key constraints are: the model degrades after ~5 weeks, training takes 12 hours, and the success metric is already computable in BigQuery (updated hourly). A weekly BigQuery scheduled query directly measures the actual business success metric at low cost, giving enough lead time to retrain before the 5-week degradation threshold is crossed. Option A (100% sample rate Vertex AI Monitoring) is unnecessarily expensive. Option B retrains every week regardless of performance, wasting compute cost. Option D (daily Dataflow jobs) is more frequent and more expensive than needed, given the 5-week degradation window.

Topics

#Model Monitoring#MLOps#Retraining Strategy#Cost Optimization

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full PROFESSIONAL-MACHINE-LEARNING-ENGINEER Practice