Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam braindumps download (PROFESSIONAL MACHINE LEARNING ENGINEER exam dumps Free)

QUESTION: 86

You are an ML engineer at a travel company. You have been researching customers’ travel behavior for many years, and you have deployed models that predict customers’ vacation patterns. You have observed that customers’ vacation destinations vary based on seasonality and holidays; however, these seasonal variations are similar across years. You want to quickly and easily store and compare the model versions and performance statistics across years.
What should you do?

Store the performance statistics in Cloud SQL. Query that database to compare the performance statistics across the model versions.
Create versions of your models for each season per year in Vertex AI. Compare the performance statistics across the models in the Evaluate tab of the Vertex AI UI.
Store the performance statistics of each pipeline run in Kubeflow under an experiment for each season per year. Compare the results across the experiments in the Kubeflow UI.
Store the performance statistics of each version of your models using seasons and years as events in Vertex ML Metadata. Compare the results across the slices.

Answer(s): D

Show Answer Next Question

QUESTION: 87

You have built a custom model that performs several memory-intensive preprocessing tasks before it makes a prediction. You deployed the model to a Vertex AI endpoint, and validated that results were received in a reasonable amount of time. After routing user traffic to the endpoint, you discover that the endpoint does not autoscale as expected when receiving multiple requests.
What should you do?

Use a machine type with more memory
Decrease the number of workers per machine
Increase the CPU utilization target in the autoscaling configurations.
Decrease the CPU utilization target in the autoscaling configurations

Answer(s): D

Show Answer Next Question

QUESTION: 88

You maintain a fraud detection model hosted on an Agent Platform endpoint. You trained the model on transaction data from the previous year. Recently, the fraud investigation team reported an increase in false negatives. You suspect that the distribution of the live transaction data has shirted significantly compared to the baseline distribution used during training. You need to validate this hypothesis using a managed service.
What should you do?

Configure the endpoint to use Model Monitoring. Enable training-serving skew detection, and provide the training dataset as the baseline.
Configure the endpoint to use Model Monitoring. Enable prediction drift detection to compare the current hour's traffic against the previous hour's traffic.
Deploy a new version of the model trained on the same data. Enable feature attribution-based monitoring in Model Monitoring to track the sampled Shapley (SHAP) value shift for each prediction.
Create a Cloud Logging sink to export the prediction request logs to BigOuery. Write a SQL query to calculate the mean and variance of the features, and compare them to the distribution of the training data.

Answer(s): A

Explanation:

Agent Platform Model Monitoring provides a managed solution for detecting training-serving skew by comparing the statistical distributions of live prediction input features against those in the original training dataset. Configuring the training dataset as the baseline allows Model Monitoring to identify significant changes in transaction feature distributions. It calculates distribution differences and detects when they exceed configured thresholds, helping validate whether training-serving skew is contributing to the increased false-negative rate. This approach enables automated monitoring and alerts without requiring custom data analysis infrastructure.

Show Answer Next Question

QUESTION: 89

Your data science team is running numerous experiments for a churn model using Agent Platform Workbench. You need to establish a workflow that ensures reproducibility of experiments, supports effective collaboration, and tracks each team member's work.
What should you do?

Use Agent Platform Experiments to track each notebook run. Instruct team members to clone a primary notebook for each new experiment.
Instruct team members to use a single, shared Agent Platform Workbench instance, and use separate conda environments to manage their library dependencies.
Store the notebooks in a version control repository, instruct team members to create a new branch for each experiment, and merge code changes by using pull requests.
Create a shared bucket in Cloud Storage to store the notebooks. Instruct the team to create their own personal folder, and append a version number as a suffix to each notebook's filename.

Answer(s): C

Explanation:

Using a version control repository such as Git provides a structured workflow for reproducible experimentation, team collaboration, and tracking individual contributions. Creating a separate branch for each experiment allows data scientists to work independently while preserving the history of notebook modifications. Pull requests enable peer review, discussion, and controlled integration of changes into the main codebase. Git's commit history records who made each change, when it occurred, and what was modified, providing traceability and allowing the team to retrieve previous notebook versions and reproduce experiments using the corresponding code.

Show Answer Next Question

QUESTION: 90

You are a lead ML engineer at a retail company. You want to track and manage ML metadata in a centralized way so that your team can have reproducible experiments by generating artifacts.
Which management solution should you recommend to your team?

Store your tf.logging data in BigQuery.
Manage all relational entities in the Hive Metastore.
Store all ML metadata in Google Cloud’s operations suite.
Manage your ML workflows with Vertex ML Metadata.

Answer(s): D

Show Answer Next Question

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps Professional Machine Learning Engineer Questions 86–90 (page: 19)

QUESTION: 86

QUESTION: 87

QUESTION: 88

Explanation:

QUESTION: 89

Explanation:

QUESTION: 90

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps
Professional Machine Learning Engineer Questions 86–90 (page: 19)