PMLE Practice Test 47 — 15 Questions

Question 1

You need to serve a large embedding model for similarity search with low latency. The model was trained to generate 256-dimensional embeddings. You plan to use Vertex AI Vector Search. Which index type should you choose to balance accuracy and performance for a dataset with 10 million vectors?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Approximate nearest neighbor (ANN) index using ScaNN. Vertex AI Vector Search uses ScaNN (Scalable Nearest Neighbors) as its underlying ANN algorithm, which is specifically designed for high-dimensional embeddings (like 256-d) and large-scale datasets (10M vectors). ScaNN balances accuracy and performance by employing anisotropic quantization and tree-based partitioning, making it the optimal choice for low-latency similarity search without requiring exhaustive comparison.

Answer

Tree-based index

Answer

Brute-force index

Answer

Hash-based index

Question 2

The exhibit shows a Vertex AI PipelineJob submission command. The pipeline fails because the component cannot find the input data. What is the most likely cause?

Accepted Answer

The input data path is not accessible by the Vertex AI Pipelines service account. The most likely cause of the pipeline failing to find input data is that the Vertex AI Pipelines service account lacks the necessary permissions to access the specified input data path. Vertex AI Pipelines uses the Compute Engine default service account (or a custom service account) to read data from Cloud Storage or other sources; if this account does not have the `storage.objectViewer` role (or equivalent) on the bucket or object, the component will fail with a permission-denied error, even if the path is syntactically correct.

Answer

The pipeline root path is incorrect

Answer

The pipeline name is misspelled

Answer

The region does not support the component

Question 3

A data scientist wants to track machine learning experiments, including parameters, metrics, and artifacts, and compare runs. Which Vertex AI service should they use?

Accepted Answer

Vertex AI Experiments. Vertex AI Experiments is designed for tracking and comparing ML experiment runs, capturing parameters, metrics, and artifacts. It integrates with MLflow for autologging.

Answer

Vertex AI Metadata

Answer

Vertex AI Feature Store

Answer

Vertex AI Model Registry

Question 4

Refer to the exhibit. A team configured Vertex AI Model Monitoring with skew detection for feature "income" with a threshold of 0.2. However, they have not received any alerts even though they suspect data drift. What is the most likely reason?

Accepted Answer

The 'income' feature is not present in the serving data. If the 'income' feature is not present in the serving data, the skew detection cannot compute a comparison, and no alert is generated even if other drifts exist. The threshold being low would increase alerts, not suppress them. The monitoring likely is enabled since the config is present. The drift threshold for drift detection is separate.

Answer

The monitoring is not enabled for the endpoint

Answer

The actual skew is below the threshold

Answer

The drift detection threshold is set higher

Question 5

An organization is building a continuous training (CT) pipeline that retrains a model whenever one of the following conditions is met: (1) new training data is available in Cloud Storage, (2) it's the first day of the month, or (3) the model's performance degrades below a threshold. Which TWO mechanisms should they combine to trigger the pipeline?

Accepted Answer

Cloud Scheduler to trigger the pipeline on a cron schedule (e.g., first day of month). Cloud Scheduler can trigger the pipeline on a cron schedule, such as the first day of every month, directly satisfying condition (2). Option E is correct because Cloud Storage Pub/Sub notifications can be configured to fire a Cloud Function whenever new training data is uploaded, satisfying condition (1). Condition (3), performance degradation, is not directly covered by any single option in the list; it would require a separate mechanism like Vertex AI Model Monitoring with Cloud Monitoring alerts. Therefore, among the given options, A and E are the best combination for the conditions that have direct native support.

Answer

Monitoring alerts from Cloud Monitoring to trigger a Cloud Function that starts the pipeline

Answer

Cloud Build trigger on code push to repository

Answer

BigQuery scheduled query to trigger the pipeline after data transformation

Question 6

A retail company wants to build a customer churn prediction model using AutoML Tables. They have a dataset with 5000 rows and 50 features, including customer ID, transaction history, and support tickets. The target is a binary column 'churned'. After training, the model shows high accuracy but low recall for the churned class. What is the most likely cause?

Accepted Answer

The churned class is underrepresented, causing the model to favor the majority class.. In imbalanced datasets, AutoML Tables optimizes for overall accuracy, which can be high if the majority class dominates. Low recall for the churned class indicates the model predicts most instances as non-churned, a classic symptom of class imbalance. AutoML Tables provides class weighting and sampling options to mitigate this, but without them, the model favors the majority class.

Answer

The dataset is too small for AutoML to train effectively.

Answer

The features are not normalized, leading to biased predictions.

Answer

The dataset includes a unique customer ID feature, causing overfitting.

Question 7

An ML team uses Vertex AI Pipelines and wants to automatically generate model cards documenting model purpose, evaluation results, and intended use. Which approach should they take?

Accepted Answer

Use Vertex AI Model Registry to generate model cards automatically from model metadata.. Vertex AI Model Registry supports model cards that can be populated programmatically via the SDK or Cloud Console.

Answer

Manually create a Google Doc and share it with the team.

Answer

Use Cloud Data Catalog to annotate the model artifact.

Answer

Write a custom Kubeflow Pipelines component that creates a BigQuery table with model metadata.

Question 8

A company uses Vertex AI Matching Engine for real-time recommendations. They need to serve queries with low latency and support frequent updates. Which two configurations are appropriate? (Choose 2)

Accepted Answer

Enable streaming updates for the index. Vertex AI Matching Engine supports streaming updates, which allow real-time insertion, deletion, and modification of vectors without rebuilding the entire index. This is essential for use cases requiring frequent updates, such as real-time recommendation systems, because it maintains low latency for serving queries while keeping the index current.

Answer

Store the index in Cloud Storage and query via Python

Answer

Use a brute-force index for exact results

Answer

Use batch updates only

Question 9

An organization runs a batch prediction job on Vertex AI for a large dataset (10 TB). The job is configured to use a cluster of 100 n1-standard-16 machines. Midway through, the job fails with 'Out of memory' errors. What is the most effective mitigation strategy?

Accepted Answer

Use a machine type with more memory per instance.. The 'Out of memory' error indicates that individual worker nodes are running out of RAM when processing their assigned data shards. Using a machine type with more memory per instance (e.g., n1-highmem-16) directly addresses the root cause by providing each node with sufficient memory to hold the model and its intermediate computations, without changing the data distribution or parallelism strategy.

Answer

Split the input data into smaller chunks and run multiple jobs.

Answer

Enable model parallelism within the prediction script.

Answer

Increase the number of machines to distribute data more.

Question 10

A retail company wants to build a recommendation system for their e-commerce website. They have user purchase history and product metadata. Which Google Cloud service is most suitable for building a 'frequently bought together' recommendation model with minimal custom ML development?

Accepted Answer

Recommendations AI with the 'frequently bought together' model type. Recommendations AI provides pre-built models for retail recommendations, including 'frequently bought together'. AutoML Tables could be used but requires more customisation. Vertex AI Prediction and BigQuery ML are not purpose-built for this use case and would require more development.

Answer

Vertex AI Prediction with a custom TensorFlow model

Answer

BigQuery ML with MATRIX_FACTORIZATION model type

Answer

Vertex AI AutoML Tables

Question 11

Which THREE of the following are supported output types for BigQuery ML?

Accepted Answer

Classification. BigQuery ML supports supervised learning tasks like classification and regression, as well as time-series forecasting, through its model types such as `LOGISTIC_REG`, `LINEAR_REG`, and `ARIMA_PLUS`. Classification (option A) is correct because BigQuery ML provides `LOGISTIC_REG` for binary and multi-class classification problems, outputting predicted labels or probabilities.

Answer

Object detection

Answer

Anomaly detection

Question 12

A company wants to monitor features in Vertex AI Feature Store for drift over time. Which two services should they use? (Choose two.)

Accepted Answer

Vertex AI Feature Store monitoring

Answer

Cloud Logging

Answer

Vertex AI Model Monitoring

Answer

Vertex AI Experiments

Question 13

A machine learning pipeline in Vertex AI produces a dataset artifact, a trained model, and evaluation metrics. The team wants to query the lineage to find all downstream artifacts that depend on a particular dataset. Which Vertex AI service should they use?

Accepted Answer

Vertex AI Metadata. Vertex AI Metadata tracks artifacts, executions, and their lineage relationships. It supports lineage queries to find upstream and downstream dependencies.

Answer

Vertex AI Feature Store

Answer

Vertex AI Experiments

Answer

Vertex AI Model Registry

Question 14

An organization uses Vertex AI Pipelines and wants to track the lineage of datasets, models, and metrics across pipeline runs. They need to query upstream and downstream dependencies of an artifact. Which service should they use?

Accepted Answer

Vertex AI Metadata. Vertex AI Metadata stores ML metadata and supports lineage queries to track the provenance of artifacts across pipeline executions.

Answer

Vertex AI Feature Store

Answer

Vertex AI Experiments

Answer

Vertex AI Model Registry

Question 15

Your team is deploying a large model on edge devices and needs to reduce its size by 80% while maintaining reasonable accuracy. Which THREE techniques should they consider? (Choose 3.)

Accepted Answer

Quantisation to INT8. Quantisation to INT8 reduces the precision of model weights and activations from 32-bit floating point to 8-bit integers, cutting memory usage by approximately 75% (4x compression). This directly addresses the 80% size reduction target while often preserving accuracy within 1-2% through careful calibration and scaling, making it a primary technique for edge deployment.

Answer

Transfer learning from a larger model

Answer

Increasing model capacity with more layers