nerdexam
Google

PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #196

You have developed a BigQuery ML model that predicts customer chum, and deployed the model to Vertex AI Endpoints. You want to automate the retraining of your model by using minimal additional code wh

The correct answer is C. 1. Create a Vertex AI Model Monitoring job configured to monitor prediction drift. To automate model retraining when feature values change and minimize retraining costs, configure a Vertex AI Model Monitoring job to detect prediction drift, which indicates changes in input data distribution.

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

Question

You have developed a BigQuery ML model that predicts customer chum, and deployed the model to Vertex AI Endpoints. You want to automate the retraining of your model by using minimal additional code when model feature values change. You also want to minimize the number of times that your model is retrained to reduce training costs. What should you do?

Options

  • A1 Enable request-response logging on Vertex AI Endpoints
  • B
    1. Enable request-response logging on Vertex AI Endpoints
  • C
    1. Create a Vertex AI Model Monitoring job configured to monitor prediction drift
  • D
    1. Create a Vertex AI Model Monitoring job configured to monitor training/serving skew

How the community answered

(26 responses)
  • A
    8% (2)
  • B
    4% (1)
  • C
    85% (22)
  • D
    4% (1)

Why each option

To automate model retraining when feature values change and minimize retraining costs, configure a Vertex AI Model Monitoring job to detect prediction drift, which indicates changes in input data distribution.

A1 Enable request-response logging on Vertex AI Endpoints

While request-response logging is necessary for model monitoring, it doesn't automate the retraining based on feature changes or minimize retraining frequency on its own.

B1. Enable request-response logging on Vertex AI Endpoints

While request-response logging is necessary for model monitoring, it doesn't automate the retraining based on feature changes or minimize retraining frequency on its own.

C1. Create a Vertex AI Model Monitoring job configured to monitor prediction driftCorrect

Vertex AI Model Monitoring can detect prediction drift, which occurs when the distribution of predictions changes over time, often due to changes in input feature distributions. Configuring a monitoring job to detect this allows for automated alerts or triggers for retraining only when significant drift is detected, minimizing unnecessary retraining and costs.

D1. Create a Vertex AI Model Monitoring job configured to monitor training/serving skew

Monitoring training/serving skew compares training and serving data distributions, but prediction drift directly addresses changes in model output due to varying input feature values over time, which is more aligned with the prompt's goal.

Concept tested: Vertex AI Model Monitoring for prediction drift

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

Topics

#Vertex AI Model Monitoring#Prediction Drift#Model Retraining#Data Drift

Community Discussion

No community discussion yet for this question.

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