How to minimize cost for model retraining?

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?

  1. Download the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model weekly.
  2. Download the weather and flu data each month. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model monthly.
  3. Download the weather and flu data each week. Configure Cloud Scheduler to execute a Vertex AI pipeline to retrain the model every month.
  4. 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. Source Reference Answer

Community Votes

D
100%

100% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.

Community Insight

The question tests cost optimization in MLOps, where the trap is selecting a fixed retraining schedule instead of a monitoring-based trigger.

To minimize retraining costs for a flu prediction model, use Vertex AI feature drift monitoring to trigger retraining only when necessary. The community consensus supports this dynamic approach over fixed schedules to optimize resource usage.

Choosing a fixed schedule (Options A, B, or C) because it is straightforward, failing to recognize that retraining only on drift saves significant costs.

Community Discussion (5 comments)

fitri001 👍 5 Selected: D
Weather Data Update: Downloading weather data weekly captures the latest trends potentially influencing flu infections. Flu Data Update: Downloading flu statistics monthly aligns with the data publication schedule and avoids unnecessary processing for data that might not have changed. Feature Drift Monitoring: Vertex AI endpoint monitoring helps identify significant changes in the weather data distribution (feature drift) over time. Retrain Based on Alerts: Retraining the model is triggered only when feature drift is detected, ensuring the model stays relevant without unnecessary retraining cycles.
pinimichele01 👍 1 Selected: D
minimize cost
guilhermebutzke 👍 1 Selected: D
My Answer: D Even though the model predicts values for the next month, it is necessary to consume weekly data because the model's output could change based on new weekly data. Therefore, it is necessary to download data weekly and monthly. Furthermore, it is not necessary to retrain the model if the feature distribution remains unchanged.
b1a8fae 👍 4 Selected: D
D. This way, cost is minimized by only retraining when feature drift takes place.
pikachu007 👍 2 Selected: D
Selective Retraining: Retraining occurs only when necessary, triggered by feature drift alerts, reducing cloud resource usage and associated costs. Efficient Data Utilization: Weather data is downloaded weekly to capture potential changes, but model retraining waits for monthly flu data, ensuring model relevance without excessive updates. Early Drift Detection: Vertex AI's feature drift monitoring proactively identifies model performance degradation, prompting timely retraining to maintain accuracy.

Comments & Corrections

No comments yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

Submitted for moderation before publishing. Keep it helpful and respectful.

Expert Analysis

Why the Answer Is Correct

Option D is the optimal solution because it aligns data ingestion with the publication frequency of the sources (weather weekly, flu monthly) and utilizes feature drift monitoring. By retraining only when a monitoring alert is detected, you ensure resources are spent only when the model's predictive power is likely compromised by data changes, directly minimizing costs.

Why the Other Options Are Wrong

Options A, B, and C propose fixed retraining schedules (weekly or monthly). While Option C aligns ingestion better than A, all fixed schedules risk incurring unnecessary compute costs by retraining even when the data distribution is stable and the model performance remains adequate. They lack the intelligence to adapt to actual data behavior.

Community Comment Notes

Community members emphasized that 'Selective Retraining' is the core concept here, noting that retraining should only occur when feature drift is detected. Comments also highlighted the importance of ingesting weather data weekly to capture potential trends, even if the target variable (flu stats) is only available monthly.

Official Reference

https://cloud.google.com/vertex-ai/docs/model-monitoring/overview

Exam Strategy

For questions focused on minimizing operational costs in MLOps, prioritize solutions that use triggers (like monitoring alerts) over fixed time intervals. Ensure the data ingestion strategy matches the availability of the specific data sources.

Related Analysis

You are developing a custom TensorFlow classification model

S-Grade

You work on a team that builds state-of-the-art deep learnin

A-Grade

You have trained an XGBoost model that you plan to deploy on

A-Grade

Practice All PMLE Questions

Access 65 questions with complete answers and detailed explanations.

View Full PMLE Practice Test →

← Back to PMLE Study Guide