PMLE Practice Test 37 — 15 Questions

Question 1

Which THREE factors should you consider when deciding between online prediction and batch prediction on Vertex AI?

Accepted Answer

Cost per prediction: batch is often cheaper per request. Latency requirements, cost structure, and data volume patterns are key factors. Instance availability is similar for both; model architecture does not dictate prediction type.

Answer

The type of machine learning model architecture (e.g., CNN vs RNN)

Answer

Availability of GPU instances in the region

Question 2

A data science team is using AI Platform for training. They want to track hyperparameters and metrics across multiple experiments. What should they use?

Accepted Answer

Vertex AI Experiments. Vertex AI Experiments is the correct choice because it is the native service within Vertex AI designed specifically for tracking, comparing, and analyzing hyperparameters and metrics across multiple training runs. It provides a centralized UI and SDK to log parameters, metrics, and artifacts, enabling systematic experiment management without manual effort or external tools.

Answer

Cloud Logging with custom metrics

Answer

Store metrics in Cloud Storage and compare manually

Answer

Cloud Monitoring dashboards

Question 3

A data engineer wants to create a BigQuery table snapshot for point-in-time recovery of a critical dataset. The snapshot should be created daily and retained for 30 days. What should they use?

Accepted Answer

BigQuery scheduled queries with CREATE SNAPSHOT. BigQuery table snapshots are created using the CREATE SNAPSHOT statement and can be scheduled with a retention period.

Answer

BigQuery copy job

Answer

BigQuery time travel

Answer

BigQuery export to Cloud Storage

Question 4

An ML engineer is using Cloud Composer (Airflow) to orchestrate a ML workflow. They need to run a Vertex AI pipeline as one of the tasks in the DAG. Which Airflow operator should they use?

Accepted Answer

VertexAIPipelineRunOperator or the Google Cloud Pipeline operator.. Cloud Composer (Airflow) natively supports the `VertexAIPipelineRunOperator` (or its alias `GoogleCloudPipelineOperator`), which is specifically designed to trigger and monitor a Vertex AI pipeline run as a task within a DAG. This operator handles authentication, pipeline job submission, and status polling without requiring custom code, making it the idiomatic choice for orchestrating Vertex AI pipelines from Airflow.

Answer

BigQueryOperator to run the pipeline as a query.

Answer

PythonOperator with a custom script using the google-cloud-aiplatform library.

Answer

VertexAIPipelineRunOperator (or Airflow's GCSToGCSOperator) for pipeline orchestration.

Question 5

You are running a Vertex AI custom training job with pre-built TensorFlow container. You want to use TPU v3 pods for faster training. Which configuration is required?

Accepted Answer

Specify machine type as tpu-v3-8 in the worker pool spec and use tf.distribute.TPUStrategy. TPU training requires specifying the TPU type in the worker pool spec and using tf.distribute.TPUStrategy in code. The pre-built container supports TPUs. Runtime version must include TPU support.

Answer

Set the worker pool machine type to n1-standard-8 and add --accelerator type=tpu

Answer

Use a custom container with TPU libraries and set --tpu-topology=v3-8

Answer

Enable TPU by setting the environment variable TPU_NAME

Question 6

A retail company uses Vertex AI AutoML to train a product recommendation model. They have a dataset of past purchases stored in BigQuery. The data science team wants to iteratively train and improve the model. They need to track which dataset version was used for each model and preserve the exact data for reproducibility. They currently export data to CSV files and store them in Cloud Storage. However, the dataset is updated daily, and they want to ensure that models are trained on a consistent snapshot. What should they do?

Accepted Answer

Use BigQuery snapshots to capture a versioned dataset and reference the snapshot in the training pipeline.. BigQuery snapshots provide a consistent, versioned view of the dataset at a specific point in time, ensuring reproducibility without duplicating data. By referencing the snapshot in the Vertex AI training pipeline, the team can train models on the exact same data snapshot, even as the source table is updated daily. This approach avoids the overhead of exporting to CSV and Cloud Storage while maintaining data integrity and lineage.

Answer

Use Vertex AI Dataset service to create a dataset and export it to BigQuery.

Answer

Train the model directly on the BigQuery table and let AutoML handle versioning.

Answer

Export the data to a timestamped CSV file and store it in Cloud Storage before each training run.

Question 7

A data science team has trained a custom TensorFlow model for real-time fraud detection. They need to deploy it on Vertex AI with minimal latency and support for multiple concurrent requests. The model requires a GPU for inference. Which machine type should they choose for the Vertex AI endpoint?

Accepted Answer

n1-standard-4 with NVIDIA T4. The n1-standard-4 with NVIDIA T4 provides the GPU acceleration required for real-time inference, while the n1 machine family supports GPU attachments on Vertex AI. The T4 GPU is optimized for low-latency inference workloads, and the n1-standard-4 offers sufficient CPU and memory for serving a custom TensorFlow model with multiple concurrent requests.

Answer

n2-standard-8

Answer

e2-standard-4

Answer

n1-highmem-4

Question 8

A company needs to serve a high-throughput prediction service with strict latency requirements. They want to minimize cold starts and ensure consistent performance. Which endpoint configuration is most appropriate?

Accepted Answer

Set min_replicas to an estimated baseline and max_replicas to a higher number. Setting min_replicas to an estimated baseline ensures that a minimum number of instances are always running, eliminating cold starts for baseline traffic. Setting max_replicas to a higher number allows the service to scale up to handle traffic spikes while maintaining consistent performance. This configuration balances cost and latency by avoiding the overhead of scaling from zero while still accommodating bursts.

Answer

Set min_replicas and max_replicas equal to a fixed number

Answer

Set min_replicas to 0 and max_replicas to a high number

Answer

Do not set min_replicas; let Vertex AI automatically determine

Question 9

A company wants to implement a document processing solution that extracts key information from invoices and receipts. They have limited ML expertise and want to use a pre-trained solution as much as possible. Which Google Cloud service should they use?

Accepted Answer

Document AI with a pre-trained invoice processor.. Document AI with a pre-trained invoice processor is the correct choice because it provides a fully managed, pre-trained solution specifically designed for extracting structured data (e.g., vendor name, invoice number, line items) from invoices and receipts. This aligns with the company's limited ML expertise and desire to use a pre-trained solution, requiring no custom model training or complex coding.

Answer

AutoML Natural Language with custom entity extraction.

Answer

Vertex AI Workbench with custom Python scripts.

Answer

Cloud Vision API with OCR.

Question 10

A data-processing pipeline using Dataflow needs to incorporate a custom ML prediction step. The team wants to maintain fast processing and minimize latency. What is the optimal approach?

Accepted Answer

Use a custom ParDo transform in Dataflow that calls Vertex AI Prediction API directly. Using a custom ParDo transform in Dataflow allows the pipeline to call the Vertex AI Prediction API synchronously within each worker, avoiding the overhead of external triggers, intermediate storage, or asynchronous messaging. This keeps the data in-memory and minimizes latency by processing predictions inline with the Dataflow streaming or batch pipeline.

Answer

Write the data to Cloud Storage, trigger a Cloud Function to call the model, and write results back

Answer

Send data to a Pub/Sub topic and have a separate subscriber that runs predictions

Answer

Stream data through Cloud Functions that serve predictions and write to BigQuery

Question 11

Refer to the exhibit. A data scientist is evaluating a binary classification model trained with BigQuery ML on an imbalanced dataset. The exhibit shows the output of ML.EVALUATE run on two different thresholds. Which TWO actions should the data scientist take to improve model performance? (Choose two.)

Accepted Answer

Use AUC-ROC as the evaluation metric instead of accuracy.. AUC-ROC is insensitive to class imbalance and evaluates the model's ability to rank positive instances higher than negative ones across all thresholds, unlike accuracy which can be misleading when the majority class dominates. In BigQuery ML, ML.EVALUATE returns metrics like accuracy, precision, recall, and AUC-ROC; for imbalanced datasets, AUC-ROC provides a more reliable measure of discriminative power.

Answer

Add more features from the source data.

Answer

Apply SMOTE oversampling in the preprocessing pipeline.

Answer

Increase the number of training iterations.

Question 12

A company deploys a model on Vertex AI Endpoints for real-time inference. They need to minimize latency for prediction requests that are identical to previous requests. Which approach should they use?

Accepted Answer

Implement a caching layer using Cloud Memorystore with request hashing.. Caching identical prediction requests using Cloud Memorystore with request hashing reduces latency by serving cached responses directly from an in-memory cache, avoiding redundant model inference. This approach is ideal for real-time inference where many requests are identical, as it bypasses the model endpoint entirely for cached requests, minimizing response time.

Answer

Use a regional load balancer with session affinity.

Answer

Use Cloud CDN to cache prediction responses.

Answer

Enable prediction caching on Vertex AI Endpoints.

Question 13

A team is using TensorFlow Transform (tf.Transform) to create preprocessing functions that will be used both in training and serving. They want to ensure consistency. Which artifact should they save after analyzing the training data?

Accepted Answer

A transform_fn SavedModel.. The correct artifact to save after analyzing training data with tf.Transform is the `transform_fn` SavedModel. This SavedModel encapsulates the exact preprocessing logic (e.g., scaling, normalization, vocabulary mapping) computed from the training dataset, ensuring that the same transformations are applied consistently during both training and serving. Without this artifact, the serving pipeline would need to recompute or duplicate the transformation logic, risking skew between training and inference.

Answer

A trained model checkpoint.

Answer

A analyzed_dataset directory with statistics.

Answer

A flattened schema file (schema.pbtxt).

Question 14

A data scientist is creating a Vertex AI pipeline using the Kubeflow Pipelines SDK v2. Which TWO statements about pipeline parameters are correct? (Choose two.)

Accepted Answer

Pipeline parameters are defined as inputs to the pipeline function decorated with @dsl.pipeline.. In the Kubeflow Pipelines SDK v2, pipeline parameters are explicitly defined as input arguments to the pipeline function that is decorated with @dsl.pipeline. These parameters serve as the primary mechanism for passing configuration values (e.g., model name, learning rate, number of epochs) into the pipeline at creation time and can be consumed by downstream components.

Answer

Pipeline parameters must be serialized to JSON before use.

Answer

Pipeline parameters can only be of type str.

Answer

Pipeline parameters can be used to pass large datasets between components.

Question 15

A data scientist has deployed a model with Vertex AI Endpoints and enabled request/response logging to BigQuery. They want to compute a confusion matrix over time to monitor model quality. What should they do?

Accepted Answer

Upload ground truth labels to BigQuery and join with prediction logs, then compute confusion matrix in a scheduled query. To compute a confusion matrix, ground truth labels are needed. The team can upload ground truth labels to BigQuery and join with prediction logs to compare predictions vs actuals.

Answer

Use Vertex AI Model Monitoring to automatically generate confusion matrices

Answer

Use Cloud Monitoring to create a confusion matrix dashboard

Answer

Enable Vertex AI Explainability to get confusion matrix