PDE Practice Test 2 — 30 Questions

Question 1

A company has a production machine learning model deployed on Vertex AI Endpoint that predicts customer churn. The model is retrained weekly using a Vertex AI Pipeline that pulls new data from BigQuery. Recently, the model's accuracy has been declining. The data science team suspects data drift but is unsure. They have enabled Vertex AI Model Monitoring but have not set up any alerts. The team wants to diagnose and address the issue quickly. The pipeline runs successfully, and no errors are reported. The model endpoint is serving predictions with average latency of 200ms. What should the team do first?

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

Accepted Answer

Review Vertex AI Model Monitoring drift reports and set up alerts for significant drift. The team has already enabled Vertex AI Model Monitoring, which automatically tracks feature distributions and prediction statistics over time. The first diagnostic step should be to review the drift reports generated by Model Monitoring to confirm whether data drift is occurring, and then set up alerts so the team is proactively notified of significant drift in the future. This directly addresses the suspected root cause without unnecessary operational changes.

Answer

Immediately trigger a retraining pipeline with more recent data

Answer

Increase the number of replicas to reduce latency

Answer

Examine Cloud Logging for prediction errors

Question 2

Which Google Cloud service is a fully managed relational database for MySQL, PostgreSQL, and SQL Server, offering automatic replication and backups?

Accepted Answer

Cloud SQL. Cloud SQL is the correct answer because it is Google Cloud's fully managed relational database service that supports MySQL, PostgreSQL, and SQL Server. It provides automatic replication across zones and automated backups, making it the ideal choice for traditional relational database workloads without the need for manual administration.

Answer

Cloud Spanner

Answer

AlloyDB

Answer

Bigtable

Question 3

A financial services company deploys a fraud detection model on Vertex AI using a custom prediction container that runs a PyTorch model. The model requires GPU acceleration. The deployment succeeds but predictions return an error: 'CUDA error: out of memory'. What should the team do to resolve this issue?

Accepted Answer

Increase the GPU machine type to one with more memory (e.g., from NVIDIA T4 to A100). The CUDA out-of-memory error indicates that the GPU's VRAM is insufficient to load the PyTorch model or process the inference batch. Increasing the GPU machine type to one with more memory, such as from an NVIDIA T4 (16 GB) to an A100 (40 or 80 GB), directly resolves the capacity issue. Vertex AI prediction endpoints allow you to select different accelerator types and sizes, and this change ensures the model fits within GPU memory.

Answer

Change the container to use a CPU-only image to avoid CUDA errors

Answer

Enable Vertex AI Model Monitoring to automatically scale the endpoint

Answer

Add CPU replicas to distribute the inferencing load

Question 4

You are designing a batch data pipeline that runs daily to ingest data from an on-premises database into BigQuery. The ingestion volume is approximately 50 GB per day. The data must be available in BigQuery by 6 AM each day. The on-premises database supports change data capture (CDC) via logs. Which approach minimizes operational cost and complexity?

Accepted Answer

Use Cloud Dataflow with a JDBC source in batch mode to read CDC logs and write to BigQuery. Using Dataflow with a JDBC source to read CDC logs in batch mode is straightforward and cost-effective for daily 50 GB loads. Dataproc could also work but requires cluster management. Pub/Sub with Dataflow would be more complex and costly for a daily batch. Data Fusion adds a visual layer but is overkill for this simple batch ingestion.

Answer

Use Cloud Dataproc with Spark Streaming to ingest CDC logs

Answer

Use Pub/Sub with a Dataflow streaming pipeline

Answer

Use Cloud Data Fusion with a batch pipeline

Question 5

Your company ingests millions of events per second into a Pub/Sub topic. The downstream consumer must process events with minimal latency and high throughput. However, the consumer occasionally falls behind during traffic spikes, and you need to ensure no data loss while minimizing costs. Which subscription type and configuration should you choose?

Accepted Answer

Pull subscription with flow control settings. Pull subscriptions allow the subscriber to control the throughput by batching messages and setting flow control, which is ideal for high-throughput scenarios. Using a pull subscription with exactly-once delivery (if available) or at-least-once combined with idempotent processing ensures no data loss. Push subscriptions have limitations on throughput and are not suitable for millions of events per second.

Answer

Push subscription with a load balancer

Answer

Push subscription with endpoint on Cloud Run

Answer

Pull subscription with exactly-once delivery disabled

Question 6

A company is using Dataflow to stream data from Cloud Pub/Sub to BigQuery. The pipeline includes a custom ParDo transformation that enriches the data with external API calls. The pipeline is experiencing high latency and occasional failures due to API timeouts. What strategy should be employed to improve reliability and performance?

Accepted Answer

Use a DoFn with stateful processing and batch API calls using asynchronous HTTP client.. Using a DoFn with stateful processing and an asynchronous HTTP client allows the pipeline to batch API calls and handle timeouts without blocking the main processing thread. This reduces latency by enabling concurrent requests and improves reliability through retry logic and state management, which is essential for external API enrichment in Dataflow.

Answer

Remove the enrichment step and store raw data in BigQuery.

Answer

Use a global window to accumulate all data before enrichment.

Answer

Increase the number of workers to parallelize API calls.

Question 7

A user gets the above error when trying to get online predictions. The model was created and the endpoint exists. What is the most likely reason?

Accepted Answer

No version of the model is deployed to the endpoint.. The error 'No version of the model is deployed to the endpoint' occurs when the endpoint exists but has no active model version assigned to it. In Google Cloud AI Platform (Vertex AI), an endpoint must have at least one deployed model version to serve predictions. Without a deployed version, the endpoint cannot handle inference requests, even though the endpoint resource exists.

Answer

The endpoint does not exist.

Answer

The endpoint is in a different region than the model.

Answer

The model does not exist.

Question 8

You are using BigQuery ML to train a matrix factorization model for a recommendation system. The training data consists of user-item interactions. You notice that the model is overfitting. Which of the following hyperparameter changes would most likely reduce overfitting?

Accepted Answer

Increase w_reg (regularization weight) from 0.1 to 0.5. Increasing the L2 regularization weight (w_reg) penalizes large weights and reduces overfitting. Increasing number of factors (num_factors) increases model complexity, worsening overfitting. Decreasing learning rate may help but not as directly as regularization.

Answer

Decrease w_reg (regularization weight) from 0.1 to 0.01

Answer

Increase num_factors from 10 to 20

Answer

Increase num_training_iterations from 10 to 20

Question 9

A financial services company runs a batch Dataflow pipeline daily to process transaction data. The pipeline reads from Cloud Storage, performs complex transformations, and writes to BigQuery. Recently, the pipeline has been failing intermittently with the error: 'Workflow failed. Causes: (9c3f7a2b1d4e): The worker missed 2000 data samples in the last 30 seconds. This can be caused by a variety of factors, including slow work items, network issues, or resource contention.' The team has already increased the number of workers and tried using e2-standard-8 machine types, but the issue persists. The pipeline processes approximately 500 GB of data per run and uses approximately 200 workers. The team suspects that the issue might be related to shuffle operations. What should the team do next to resolve the issue?

Accepted Answer

Increase the persistent disk size per worker to 100 GB.. The error indicates that workers are missing data samples due to slow shuffle operations, often caused by insufficient disk I/O. Increasing the persistent disk size per worker to 100 GB provides more local scratch space for Dataflow's shuffle, reducing disk contention and allowing the shuffle to complete within the 30-second window. This directly addresses the root cause without changing the worker count or machine type.

Answer

Enable Streaming Engine for the pipeline.

Answer

Reduce the number of workers to 100 to decrease shuffle overhead.

Answer

Use Cloud Storage as a shuffle sink.

Question 10

You need to analyze customer churn and want to understand the rank of each customer's churn probability within their subscription plan. Which BigQuery window function computes the relative ranking from 1 (highest probability) to N?

Accepted Answer

RANK(). RANK() assigns a rank with gaps for ties; DENSE_RANK() assigns consecutive ranks; ROW_NUMBER() assigns unique sequential numbers; NTILE() divides into buckets. For relative ranking with ties, RANK() is typically used for 'rank' meaning.

Answer

DENSE_RANK()

Answer

NTILE(100)

Answer

ROW_NUMBER()

Question 11

A data engineer is preparing a dataset for ML training in Vertex AI. The dataset includes a timestamp column, a categorical column with high cardinality (1000 distinct values), and a numerical column with outliers. Which two preprocessing steps should they apply? (Choose TWO)

Accepted Answer

Label encode the categorical column. One-hot encoding for high cardinality may be too sparse; label encoding (ordinal encoder) is more common. Winsorizing clips outliers.

Answer

Drop the timestamp column

Answer

Normalize the numerical column using Z-score

Answer

One-hot encode the categorical column

Question 12

A company runs a Dataflow pipeline that reads from Pub/Sub, aggregates events in a 10-minute fixed window, and writes to BigQuery. Recently, the pipeline has been failing with 'high uncommitted bytes' errors during periods of high traffic. What is the most likely cause and recommended action?

Accepted Answer

Use a global window with a trigger that fires early based on element count to reduce the number of open windows.. The 'high uncommitted bytes' error in Dataflow occurs when the system holds too much data in memory across many open windows, exceeding the default 200 MB limit. Using a global window with an early trigger based on element count reduces the number of simultaneous open windows and allows data to be committed more frequently, preventing memory pressure. This approach is recommended over reducing window size or scaling workers because the root cause is window fan-out, not throughput or parallelism.

Answer

Reduce the window size from 10 minutes to 1 minute to decrease the amount of data per window.

Answer

Increase the number of worker machines to handle higher throughput.

Answer

Set a maximum number of workers and use a Pub/Sub flow control setting to limit incoming messages.

Question 13

Refer to the exhibit. A team is trying to run a custom prediction container on Vertex AI Endpoint. They get this error when the container starts. What is the most likely cause?

Accepted Answer

The entry point is missing or incorrect. The error occurs when the container starts, which typically happens during the initial health check or readiness probe. Vertex AI Endpoints require a valid entry point (e.g., CMD or ENTRYPOINT in the Dockerfile) to start the prediction server. If the entry point is missing or incorrect, the container fails to launch, resulting in the observed error.

Answer

The container image is too large

Answer

The container is built for a different CPU architecture

Answer

The model file is missing from the container

Question 14

A data engineer is building a Cloud Workflows workflow that orchestrates multiple Cloud Functions and API calls. The workflow should handle transient failures with retries and send a notification to a Pub/Sub topic if the workflow ultimately fails. Which THREE steps should the engineer include in the workflow definition?

Accepted Answer

Use the 'googleapis.pubsub.v1.projects.topics.publish' connector to send a failure notification.. Workflows supports retry policies via 'retry' blocks, conditional steps using 'switch', and Pub/Sub publishing via the 'googleapis.pubsub.v1.projects.topics.publish' connector. The 'try/catch' is not a Workflows construct; instead, use 'step' with 'retry' and 'on_error' for failure handling. 'for' loops are for iteration, not error handling.

Answer

Use a 'for' loop to iterate over retries.

Answer

Use a 'try' / 'catch' block to handle exceptions and route to a failure step.

Question 15

A company uses Cloud Composer (Airflow) to orchestrate pipelines. They want to implement a pattern where a task polls for a file arrival in Cloud Storage and then triggers subsequent tasks. Which THREE Airflow concepts are essential? (Choose 3)

Accepted Answer

Sensors (e.g., GCSObjectExistenceSensor). A is correct because Sensors are a specialized type of operator designed to wait for a specific condition, such as file arrival in Cloud Storage. The `GCSObjectExistenceSensor` in Cloud Composer (Airflow) polls Google Cloud Storage at a configurable interval until the target file exists, making it the precise tool for this file-arrival polling pattern.

Answer

Operators (e.g., PythonOperator)

Answer

SubDAGs for grouping tasks

Question 16

Your company uses Vertex AI Pipelines to automate model retraining. The pipeline has three steps: data extraction from BigQuery, feature engineering using Dataflow, and model training using a custom container on Vertex AI Training. Recently, the pipeline has been failing intermittently at the Dataflow step with a 'The job encountered a transient error. Please retry.' message. You have enabled pipeline retries with 3 attempts. However, the pipeline still fails after 3 retries. You check the logs and find that the Dataflow job requires more resources than the default worker configuration provides. Which change should you make to reduce the failure rate?

Accepted Answer

Increase the Dataflow worker machine type to have more memory and CPU in the pipeline step configuration. The pipeline fails due to insufficient resources (memory and CPU) in the default Dataflow worker configuration. By increasing the worker machine type (e.g., using a custom machine type with more vCPUs and memory), the Dataflow job can handle the feature engineering workload without hitting resource limits, reducing transient failures. This directly addresses the root cause identified in the logs, unlike retries or parallelism changes.

Answer

Increase the number of Dataflow workers to improve parallelism

Answer

Increase the number of retries in the pipeline to 5

Answer

Replace Dataflow with Dataproc to run the feature engineering step

Question 17

A production model deployed on Vertex AI Endpoint is experiencing high latency during traffic spikes. The current configuration uses a single replica. What is the most efficient solution?

Accepted Answer

Enable autoscaling with minReplicaCount=1 and maxReplicaCount=10. Enabling autoscaling with minReplicaCount=1 and maxReplicaCount=10 allows Vertex AI Endpoint to dynamically add replicas during traffic spikes, distributing inference requests across multiple instances and reducing latency. This is the most efficient solution as it scales resources up only when needed, avoiding over-provisioning and minimizing cost during low traffic periods.

Answer

Set a higher min replica count (e.g., 3)

Answer

Use a larger machine type (e.g., n1-highmem-8)

Answer

Switch to batch prediction to handle spikes

Question 18

Which THREE of the following are best practices when designing a Cloud Dataflow pipeline for batch processing? (Choose three.)

Accepted Answer

Use side inputs to hold a large lookup table that is read in every element.. Side inputs in Cloud Dataflow are designed to efficiently broadcast a read-only dataset (like a lookup table) to all parallel workers. When the side input is a large but static dataset, Dataflow can cache it in memory or on disk across workers, avoiding repeated external lookups and reducing per-element processing overhead. This pattern is especially effective for batch processing where the side input is read once and reused across all elements.

Answer

Use mutable state within ParDo to track running totals.

Answer

Always insert a Reshuffle transform after every GroupByKey to redistribute data.

Question 19

Which TWO best practices should be followed when managing multiple model versions on Vertex AI Endpoints for a production system?

Accepted Answer

Use traffic splitting to gradually shift traffic to a new version while monitoring performance.. Vertex AI Endpoints support traffic splitting, allowing you to route a percentage of inference requests to a new model version while the rest goes to the existing version. This enables gradual rollout, monitoring of performance metrics (e.g., latency, error rate), and safe rollback without downtime. It is a best practice for production systems to validate a new version before fully cutting over.

Answer

Always keep all historical versions deployed to enable fast rollback.

Answer

If two versions share the same endpoint, they must have exactly the same machine type.

Answer

Use the same endpoint for multiple versions and adjust min_replica_count, max_replica_count for each version.

Question 20

A data engineer needs to automatically delete objects from a Cloud Storage bucket after 30 days and archive them to nearline storage after 7 days. Which configuration should they use?

Accepted Answer

Set a lifecycle rule to SetStorageClass to nearline after 7 days and delete after 30 days. It implements a lifecycle rule that first transitions objects to Nearline storage after 7 days (reducing costs for infrequently accessed data) and then deletes them after 30 days. This matches the requirement to archive after 7 days and delete after 30 days, using the `SetStorageClass` and `Delete` actions in the correct chronological order.

Answer

Set a lifecycle rule to SetStorageClass to nearline after 30 days only

Answer

Set a lifecycle rule to delete objects after 7 days only

Answer

Set a lifecycle rule to delete objects after 7 days and SetStorageClass to nearline after 30 days