PMLE Practice Test 41 — 15 Questions

Question 1

An organization wants to trigger a Vertex AI pipeline whenever new data arrives in a Cloud Storage bucket. Which approach should they use?

Accepted Answer

Use Cloud Functions triggered by Cloud Storage events to call the Vertex AI pipeline API.. Cloud Functions can be directly triggered by Cloud Storage events (e.g., `google.storage.object.finalize`) and can then call the Vertex AI pipeline API using the Cloud SDK or client libraries. This provides a serverless, event-driven architecture that reacts immediately to new data without polling or additional infrastructure.

Answer

Configure a Vertex AI pipeline trigger directly on the bucket using the GCP Console.

Answer

Use Pub/Sub notifications from the bucket and a Dataflow job to start the pipeline.

Answer

Set up a Cloud Scheduler job that runs every minute and checks for new files in the bucket.

Question 2

A team trains a distributed TensorFlow model using the config above. After training, they deploy the model for online predictions. The model returns poor quality predictions. They suspect that the model was not trained correctly due to a configuration error. What is the most likely mistake?

Accepted Answer

The `scaleTier` is set to 'STANDARD_1' which only supports up to 3 workers.. The `scaleTier` set to 'STANDARD_1' only supports a maximum of 3 workers, but the configuration specifies 10 workers. This mismatch causes the training job to either ignore the worker count and run with fewer workers or fail to allocate the intended resources, leading to an undertrained model and poor predictions. Option B is incorrect because the use of a custom container is not inherently problematic. Option C is incorrect because a `--model-export-path` is not required; the model directory is specified separately. Option D is incorrect because the parameter server count does not need to equal the worker count; it can be smaller.

Answer

The training job is using a custom container that does not match the requirements.

Answer

The model was exported incorrectly because the training job did not specify a `--model-export-path`.

Answer

The parameter server count should be at least equal to the worker count.

Question 3

A financial institution uses a machine learning model to approve loans. They must monitor for fairness and bias. Which THREE Google Cloud tools or features can help them achieve this? (Choose 3.)

Accepted Answer

What-If Tool. The What-If Tool (WIT) is a Google Cloud tool integrated with Vertex AI that allows users to analyze model behavior across different subsets of data, such as demographic groups. It provides interactive visualizations to test how changes in input features affect predictions, enabling fairness assessments by comparing performance metrics across groups. This directly supports monitoring for bias in loan approval decisions.

Answer

Cloud Data Loss Prevention

Answer

Cloud Healthcare API

Question 4

Refer to the exhibit. A data scientist runs this Vertex AI training job code. What will be the outcome?

Accepted Answer

A HyperparameterTuningJob is created and runs trials.. The code uses `HyperparameterTuningJob` with `parallel_trial_count=1` and `max_trial_count=10`. This creates a hyperparameter tuning job that runs up to 10 trials, each trial being a separate training run with different hyperparameter values. The `parallel_trial_count=1` means trials run sequentially, not in parallel, but this is valid and does not cause failure.

Answer

The job runs as a regular custom training with 10 replicas.

Answer

A CustomJob is created with hyperparameters from the spec.

Answer

The job fails because parallel_trial_count cannot be less than max_trial_count.

Question 5

A team of ML engineers is building a real-time fraud detection system. They use Cloud Pub/Sub to stream transactions, Dataflow for feature engineering, and Vertex AI to get predictions. They want to ensure that the data used for training matches the data used for serving to avoid training-serving skew. Which approach should they take?

Accepted Answer

Use Vertex AI Feature Store to store features computed during training and retrieve them in the serving pipeline.. Vertex AI Feature Store ensures that the same feature engineering logic is applied consistently during both training and serving. By storing precomputed features in the Feature Store, the serving pipeline retrieves the exact same feature values that were used during training, eliminating the risk of training-serving skew. This approach is specifically designed for real-time systems where streaming data (via Pub/Sub and Dataflow) must be served with identical transformations.

Answer

Use a batch processing system for both training and serving to ensure identical feature calculations.

Answer

Implement separate feature engineering pipelines for training and serving, but document them carefully.

Answer

Ensure that both training and serving read from the same Cloud Storage location.

Question 6

A financial services company uses BigQuery ML to build a logistic regression model for fraud detection. The model is trained on the last 6 months of transaction data (about 50 million rows). After deployment, the fraud detection team notices a high false positive rate, causing customer dissatisfaction and extra manual review costs. The model is currently retrained monthly. The team wants to reduce false positives without sacrificing recall. They have access to real-time transaction streaming and can compute new features quickly. What is the most effective approach?

Accepted Answer

Add engineered features like rolling transaction count and velocity per user. Adding engineered features like rolling transaction count and velocity per user directly addresses the high false positive rate by providing the logistic regression model with more discriminative temporal signals. Since the team has access to real-time streaming and can compute features quickly, these features capture behavioral patterns that reduce false positives without sacrificing recall, and logistic regression can effectively leverage them with proper feature engineering.

Answer

Replace logistic regression with gradient boosted trees (XGBoost) in BigQuery ML

Answer

Use Vertex AI AutoML Tables to train a more complex model

Answer

Increase retraining frequency to daily

Question 7

An ML engineer wants to monitor the performance of a Vertex AI Endpoint. Which TWO metrics are available in Cloud Monitoring for Vertex AI Endpoints? (Choose 2)

Accepted Answer

Error count. Cloud Monitoring for Vertex AI Endpoints includes metrics like prediction latency (p50, p95, p99) and error count/rate. CPU/GPU utilization is also available for endpoint machines.

Answer

Model accuracy

Answer

Feature skew score

Answer

SHAP values

Question 8

A machine learning engineer is designing an ML pipeline on Vertex AI. The pipeline includes multiple steps: data validation, preprocessing, training, evaluation, and deployment. The engineer wants to ensure that if the data validation step fails due to schema mismatch, the pipeline stops immediately and does not proceed. Additionally, they want to reuse the preprocessed data from a previous successful run if the source data hasn't changed. Which two configurations should they use? (Choose two.)

Accepted Answer

Set the 'on_failure' parameter of the data validation component to 'Stop'.. The correct options are B and D. Option B: Setting the 'on_failure' parameter of the data validation component to 'Stop' causes the pipeline to immediately abort when data validation fails, which meets the requirement. Option D: Setting 'cache' to True on the preprocessing step enables Vertex AI's caching mechanism, which reuses outputs from previous runs if the input data and component code are unchanged, effectively skipping reruns when source data hasn't changed. Option A is incorrect because custom exit handlers are not a standard pipeline feature; the correct way to abort on failure is via the 'on_failure' parameter. Option C is incorrect because conditional branches add complexity and are not the simplest approach; the 'on_failure' parameter directly stops the pipeline. Option E is incorrect because 'skip_if_successful' is not a valid parameter; caching achieves the desired reuse behavior.

Answer

Use a custom exit handler in the data validation step to abort the pipeline.

Answer

Use conditional branches to check the output of data validation before proceeding.

Answer

Enable 'skip_if_successful' on the preprocessing step.

Question 9

A healthcare company uses AutoML Tables to predict patient readmission risk. The dataset contains 500,000 rows and 200 features, including patient demographics, lab results, and medical history. The model accuracy is lower than expected. The engineer wants to improve performance using low-code techniques. Which THREE actions are most effective? (Choose THREE.)

Accepted Answer

Remove highly correlated features using AutoML Tables' built-in feature importance analysis.. AutoML Tables provides built-in feature importance analysis that can identify and remove highly correlated features, which reduces noise and multicollinearity, often improving model performance without manual intervention. This is a low-code technique that leverages the platform's automated capabilities to streamline feature selection.

Answer

Increase the training time budget to the maximum allowed.

Answer

Use a custom model architecture via AutoML Tables advanced options.

Question 10

A team uses Vertex AI Pipelines for continuous training triggered by model drift. They want to monitor the pipeline execution cost and optimize resource usage. Which THREE metrics should they track? (Choose 3)

Accepted Answer

Pipeline execution duration. Training cost is influenced by GPU hours, machine type, and training duration. Tracking these helps optimize.

Answer

Number of failed pipeline runs

Answer

Model accuracy on validation set

Question 11

Your organization has a requirement to monitor fairness of an ML model that predicts loan approvals. You need to set up alerts if the model's predictions show bias against a protected group. Which tool on Google Cloud can you use to monitor this?

Accepted Answer

Vertex AI Model Monitoring with Fairness Indicators integration.. Vertex AI Model Monitoring with Fairness Indicators integration is the correct tool because it allows you to continuously monitor a deployed model's predictions for bias against protected groups (e.g., race, gender) by analyzing prediction distributions and setting alert thresholds. This is a post-deployment monitoring capability, not a training-time evaluation, and it directly addresses the requirement to set up alerts on live predictions.

Answer

Cloud Vision API to analyze demographic data.

Answer

AutoML Tables fairness evaluation results from training.

Answer

Cloud DLP (Data Loss Prevention) to inspect input features for bias.

Question 12

A data scientist is using Vertex AI Workbench user-managed notebooks. They need to collaborate with a colleague on the same notebook. The colleague should be able to edit the notebook simultaneously. What should they do?

Accepted Answer

Share the notebook instance URL with the colleague; both can edit simultaneously. Vertex AI Workbench user-managed notebooks support real-time collaboration by sharing the notebook instance URL. When you share the URL with a colleague, both users can edit the notebook simultaneously because the underlying JupyterLab environment is multi-user and supports concurrent editing sessions. This is the intended method for synchronous collaboration on the same notebook instance.

Answer

Store the notebook in Cloud Source Repositories and have the colleague clone it

Answer

Share the underlying Compute Engine VM's SSH access with the colleague

Answer

Export the notebook to Colab and share the link

Question 13

A data analyst wants to use Vision API to detect custom objects in manufacturing images, but the pre-trained API does not recognize their specific components. They have 1000 labeled images. Which path offers the fastest time-to-value with minimal coding?

Accepted Answer

Use AutoML Vision for object detection. AutoML Vision for object detection is the fastest path because it requires no custom coding—users simply upload labeled images, and the platform automatically trains a model tailored to their custom components. This directly addresses the need to detect objects the pre-trained Vision API cannot recognize, while minimizing time-to-value compared to manual TensorFlow training or custom infrastructure setup.

Answer

Store images in BigQuery and use ML.PREDICT with a custom model

Answer

Use a Cloud Function to call the Vision API and post-process results

Answer

Train a custom object detection model using TensorFlow on Vertex AI

Question 14

Refer to the exhibit. A team runs the command above and sees only two models. They know there is a model 'model-v3' created three days ago. What is the most likely reason it is not listed?

Accepted Answer

The model was created in a different region.. The `gcloud ai models list` command lists models within a specific region, as Vertex AI models are regional resources. If 'model-v3' was created in a different region, it would not appear in the output unless the `--region` flag is set to that region. This is the most likely reason the model is missing from the list.

Answer

The model is in a different project.

Answer

The model is not deployed to an endpoint.

Answer

The model's display name contains a hyphen.

Answer

The model was created by a different user.

Question 15

A marketing team wants to analyze customer reviews for sentiment without writing code. Which Google Cloud service should they use?

Accepted Answer

Cloud Natural Language API. The Cloud Natural Language API (option D) is the correct choice because it provides pre-trained models for sentiment analysis, entity recognition, and syntax analysis via a simple REST API, requiring no code beyond sending HTTP requests. This aligns perfectly with the requirement to analyze customer reviews for sentiment without writing code, as the API abstracts all ML complexity.

Answer

Cloud Dataflow

Answer

Vertex AI Workbench

Answer

BigQuery ML