PDE Operationalizing machine learning models Practice Test 4 — 15 Questions

Question 1

Match each BigQuery feature to its description.

Question 2

A data scientist has trained an XGBoost model on Vertex AI and wants to deploy it to an endpoint with automatic scaling based on traffic. What is the recommended deployment approach?

Accepted Answer

Use Vertex AI Endpoints with automatic scaling enabled. Vertex AI Endpoints with automatic scaling enabled is the recommended approach because it directly supports deploying trained models (including XGBoost) as online prediction endpoints with built-in autoscaling based on incoming traffic. This service manages the underlying infrastructure, load balancing, and scaling policies, aligning with the requirement for automatic scaling without additional containerization or serverless overhead.

Answer

Export the model to a container and deploy on Cloud Run

Answer

Use AI Platform Prediction with batch prediction

Answer

Deploy the model as an API on App Engine

Question 3

A retail company is using a machine learning model for inventory forecasting. They observe that the model's predictions become less accurate over time, especially during holiday seasons. Which monitoring metric should they prioritize?

Accepted Answer

Prediction drift (feature drift). Prediction drift (feature drift) is the correct metric because it directly measures changes in the input data distribution over time, which is the root cause of degrading model accuracy during holiday seasons. When customer behavior shifts (e.g., buying patterns during holidays), the features the model relies on drift, causing predictions to become less accurate. Monitoring prediction drift allows the team to detect when retraining or updating the model is necessary.

Answer

Model latency

Answer

Prediction counts

Answer

Resource utilization

Question 4

A financial institution needs to deploy a TensorFlow model for fraud detection with strict latency requirements (<100ms). The model uses custom ops that are not available in standard TF Serving. What is the most appropriate serving solution?

Accepted Answer

Use NVIDIA Triton Inference Server with a custom backend. Option C is correct because NVIDIA Triton Inference Server supports custom backends written in C++ or Python, allowing the integration of custom ops that are not available in standard TensorFlow Serving. This enables the model to meet strict latency requirements (<100ms) by leveraging GPU acceleration and optimized inference pipelines, while avoiding the limitations of TF Serving's fixed op registry.

Answer

Export the model as a SavedModel and serve on Vertex AI Prediction

Answer

Use Cloud Run with a custom container that includes the model and pre-loads the library

Answer

Package the model with Docker using TF Serving and add custom ops via TensorFlow's custom op registration

Question 5

A team is using Kubeflow Pipelines on Google Kubernetes Engine to orchestrate ML workflows. They need to track parameters, metrics, and artifacts for each run. Which tool should they integrate?

Accepted Answer

Vertex ML Metadata. Vertex ML Metadata is the correct choice because it is purpose-built for tracking parameters, metrics, and artifacts in ML workflows, and it integrates natively with Kubeflow Pipelines on Google Kubernetes Engine. It stores metadata for each pipeline run, enabling lineage tracking, comparison, and reproducibility of experiments.

Answer

Cloud Monitoring

Answer

Cloud Logging

Answer

BigQuery

Question 6

A company has a trained model stored in Vertex AI Model Registry. They want to automate retraining when new training data arrives in Cloud Storage. Which approach is most efficient?

Accepted Answer

Use Cloud Functions triggered by Cloud Storage events to start a Vertex AI Training job. Cloud Functions can be directly triggered by Cloud Storage events (e.g., object finalize) to invoke the Vertex AI Training service via the AI Platform API. This creates an event-driven, serverless pipeline that retrains the model immediately when new data arrives, without polling or manual intervention, making it the most efficient and cost-effective approach.

Answer

Use Dataflow to continuously update the model

Answer

Use Cloud Scheduler to trigger a Cloud Build retraining step

Answer

Schedule a weekly Cloud Composer DAG to check for new data and retrain

Question 7

An e-commerce company deploys a recommendation model on Vertex AI Endpoints. The endpoint receives a high volume of requests with a large payload. They notice high latency and occasional timeouts. Which action should they take to improve performance without sacrificing accuracy?

Accepted Answer

Enable request batching on the endpoint. Enabling request batching on the Vertex AI endpoint allows multiple inference requests to be grouped into a single prediction call, reducing per-request overhead and improving throughput. This directly addresses high latency and timeouts caused by a high volume of large payloads without altering the model or its accuracy.

Answer

Switch to a smaller machine type

Answer

Reduce the model size by pruning

Answer

Increase the number of replicas

Question 8

A startup is deploying a PyTorch model on Google Cloud. They need to serve predictions for a mobile app with bursty traffic. Which service is most cost-effective?

Accepted Answer

Vertex AI Endpoints with autoscaling and a minimum of 0 replicas to scale down to zero. Option D is correct because Vertex AI Endpoints with autoscaling and minimum replicas set to 0 can scale down to zero when idle, reducing cost. Option A has minimum replicas, incurring cost. Options B and C may not scale to zero or lack ML optimization.

Answer

Vertex AI Endpoints with a minimum number of replicas

Answer

App Engine with manual scaling

Answer

Cloud Run with CPU always allocated

Question 9

A data scientist is using Vertex AI to train a model and wants to ensure that the training code and environment are reproducible. Which approach should they take?

Accepted Answer

Use Vertex AI Training with a pre-built container and specify the exact version of the framework. Option B is correct because pre-built containers with specific versions ensure the exact same environment across runs. Option A with custom containers is good but less standard. Options C and D are not best practices for reproducibility.

Answer

Use Jupyter notebooks on Vertex AI Workbench

Answer

Use custom containers with fixed tags

Answer

Use Cloud Build to train the model

Question 10

A healthcare organization is deploying a model that processes protected health information (PHI). They need to ensure that the inference data is encrypted in transit and at rest, and access is audited. Which combination of services meets these requirements?

Accepted Answer

Vertex AI Endpoints with VPC-SC, CMEK, and Cloud Audit Logs. Option C is correct because VPC Service Controls (VPC-SC) provides data exfiltration protection and ensures inference data remains within a defined security perimeter, Customer-Managed Encryption Keys (CMEK) encrypt data at rest with keys controlled by the organization, and Cloud Audit Logs capture all access events for auditing. This combination directly addresses encryption in transit (via VPC-SC perimeter enforcement) and at rest (via CMEK), plus access auditing via Cloud Audit Logs.

Answer

Cloud Run with VPC connector and Cloud KMS

Answer

Vertex AI Endpoints with IAM and Cloud Monitoring

Answer

AI Platform Prediction with Cloud Armor

Question 11

A team is debugging a sudden increase in prediction latency for a model deployed on Vertex AI Endpoints. Which TWO metrics in Cloud Monitoring should they examine first? (Choose two.)

Accepted Answer

CPU utilization. CPU utilization (A) is correct because a sudden increase in prediction latency often stems from the model consuming excessive CPU cycles during inference, especially for compute-intensive models like deep neural networks. Monitoring CPU utilization helps identify whether the endpoint's compute resources are saturated, causing requests to queue and latency to spike. Memory utilization (B) is correct because insufficient memory can lead to swapping or garbage collection pauses, directly increasing latency. Vertex AI Endpoints autoscales based on these metrics, so examining them first pinpoints resource bottlenecks.

Answer

gRPC port errors

Answer

Number of predictions

Answer

Prediction request latency

Question 12

A company is migrating ML workflows to Vertex AI Pipelines. They want to ensure best practices for pipeline reproducibility and debugging. Which THREE actions should they take? (Choose three.)

Accepted Answer

Set a random seed for all training components. Setting a random seed for all training components ensures deterministic behavior, meaning that the same inputs will produce the same outputs across multiple runs. This is critical for debugging and reproducibility in Vertex AI Pipelines, as it eliminates stochastic variability that can mask bugs or make results irreproducible. Without a fixed seed, even identical code and data can yield different model weights or metrics, complicating root cause analysis.

Answer

Use dynamic pipeline parameters for each run

Answer

Use conditional execution based on previous component outputs

Question 13

A data engineering team is operationalizing a machine learning model for real-time inference. They need to monitor the model's performance in production. Which THREE types of monitoring should they implement? (Choose three.)

Accepted Answer

Model accuracy decay. Model accuracy decay (A) is critical because in production, the model's predictive performance can degrade over time due to changes in the underlying data distribution or business logic. Monitoring accuracy decay allows the team to detect when the model no longer meets its performance baseline, triggering retraining or rollback. This is a standard practice in MLOps for maintaining model reliability.

Answer

Model re-training frequency

Answer

Training pipeline failures

Question 14

Refer to the exhibit. An ML engineer sees this error when invoking a Vertex AI endpoint. What is the most likely cause?

Accepted Answer

The model expects 128x128 images but raw input is 256x256. The error indicates a mismatch between the input dimensions expected by the model and the dimensions of the data being sent to the Vertex AI endpoint. ResNet50 models are commonly trained on 128x128 images, and if the raw input is 256x256, the endpoint will reject the request because the model's input tensor shape does not match. This is a typical input validation error in Vertex AI, where the serving infrastructure checks the shape of the prediction request against the model's signature.

Answer

The input format should be JSON

Answer

The model has a bug in the ResNet50 architecture

Answer

The endpoint is overloaded

Question 15

Refer to the exhibit. A data scientist notices that the evaluation component rarely passes the threshold, causing the pipeline to fail often. What should they do to improve efficiency?

Accepted Answer

Add a conditional component that only runs evaluation if training metrics are above a certain level. Adding a conditional component that only runs evaluation when training metrics exceed a certain threshold prevents unnecessary evaluation runs on poorly performing models. This reduces pipeline failures by ensuring that evaluation, which may be resource-intensive or prone to failure with low-quality inputs, is only triggered when the model has demonstrated sufficient training performance. This approach optimizes resource usage and pipeline reliability without sacrificing the evaluation step entirely.

Answer

Reduce the training dataset size

Answer

Remove the evaluation component

Answer

Increase the threshold value