Professional Machine Learning Engineer Free Practice Questions — Page 5
Question 17
You are an AI engineer with an apparel retail company. The sales team has observed seasonal sales patterns over the past 5-6 years. The sales team analyzes and visualizes the weekly sales data stored in CSV files. You have been asked to estimate weekly sales for future seasons to optimize inventory and personnel workloads. You want to use the most efficient approach. What should you do?
A. Upload the files into Cloud Storage. Use Python to preprocess and load the tabular data into BigQuery. Use time series forecasting models to predict weekly sales.
B. Upload the files into Cloud Storage. Use Python to preprocess and load the tabular data into BigQuery. Train a logistic regression model by using BigQuery ML to predict each product's weekly sales as one of three categories: high, medium, or low.
C. Load the files into BigQuery. Preprocess data by using BigQuery SQL. Connect BigQuery to Looker. Create a Looker dashboard that shows weekly sales trends in real time and can slice and dice the data based on relevant filters.
D. Create a custom conversational application using Vertex AI Agent Builder. Include code that enables file upload functionality, and upload the files. Use few-shot prompting and retrieval-augmented generation (RAG) to predict future sales trends by using the Gemini large language model (LLM).
Show Answer
Correct Answer: A
Explanation: The task is to forecast future weekly sales from historical seasonal time series data. Time series forecasting models are specifically designed for this use case and are the most appropriate and efficient choice. Logistic regression is for classification rather than forecasting numeric sales values, Looker provides visualization rather than prediction, and using an LLM with RAG is unnecessary and not appropriate for structured time series forecasting.
Question 17
You have deployed a deep learning model to an Agent Platform endpoint using a machine type with NVIDIA GPUs. You initially configured the endpoint to autoscale based on a target CPU utilization of 60%. During a load test, you observe that prediction latency increases significantly as traffic rises, but the number of replicas remains constant. Cloud Monitoring indicates that CPU utilization stays below 40%, while the GPU utilization consistently exceeds 90%. You need to ensure that the endpoint scales efficiently to handle the increased load. What should you do?
A. Update the autoscaling configuration to scale based on the GPU duty cycle metric.
B. Update the autoscaling configuration to decrease the target CPU utilization to 20%.
C. Redeploy the model to a machine type that includes a TPU.
D. Increase the minimum replica count for the endpoint to match the peak load that was observed during testing.
Show Answer
Correct Answer: A
Explanation: GPU utilization is the bottleneck, while CPU utilization remains below the configured target. Configure autoscaling to use GPU duty cycle so the endpoint adds replicas as GPU demand rises. Lowering the CPU target would not address the GPU bottleneck, and setting a high minimum replica count would provision capacity regardless of demand.
Question 18
You are building an ML model to predict customer churn for a subscription service. You have trained your model on Vertex AI using historical data, and deployed it to a Vertex AI endpoint for real-time predictions. After a few weeks, you notice that the model's performance, measured by AUC (area under the ROC curve), has dropped significantly in production compared to its performance during training. How should you troubleshoot this problem?
A. Monitor the training/serving skew of feature values for requests sent to the endpoint.
B. Monitor the resource utilization of the endpoint, such as CPU and memory usage, to identify potential bottlenecks in performance.
C. Enable Vertex Explainable AI feature attribution to analyze model predictions and understand the impact of each feature on the model's predictions.
D. Monitor the latency of the endpoint to determine whether predictions are being served within the expected time frame.
Show Answer
Correct Answer: A
Explanation: A significant degradation in production AUC after deployment commonly indicates data drift or training-serving skew. Vertex AI Model Monitoring can detect differences between feature distributions seen during training and those observed in online prediction requests, helping identify whether the model is receiving data that differs from what it was trained on. CPU/memory utilization and latency affect service performance, not model accuracy, and Explainable AI helps interpret predictions rather than diagnose production performance degradation due to distribution changes.
Question 18
Your company manages an ecommerce platform and has a large dataset of customer reviews. Each review has a positive, negative, or neutral label. You need to quickly prototype a sentiment analysis model that accurately predicts the sentiment labels of new customer reviews while minimizing time and cost. What should you do?
A. Use the Agent Platform Text Embeddings API to vectorize the text, and train a regression model by using Agent Platform AutoML to predict sentiment scores.
B. Use Agent Platform AutoML to train a multi-class classification model that predicts sentiment labels based on the training data.
C. Use the Natural Language API for real-time sentiment analysis.
D. Train a sentiment analysis model by using a BERT-based model, and fine-tune the model by using domain-specific customer reviews.
Show Answer
Correct Answer: B
Explanation: Use AutoML to train a multi-class classification model on the labeled reviews. It directly predicts the positive, negative, and neutral labels with minimal model-development effort, making it suitable for a quick, cost-conscious prototype.
Question 19
You are an ML researcher and are evaluating multiple deep learning-based model architectures and hyperparameter configurations. You need to implement a robust solution to track the progress of each model iteration, visualize key metrics, gain insights into model internals, and optimize training performance.
You want your solution to have the most efficient and powerful approach to compare the models and have the strongest visualization abilities. How should you bull this solution?
A. Use Vertex AI TensorBoard for in-depth visualization and analysis, and use BigQuery for experiment tracking and analysis.
B. Use Vertex AI TensorBoard for visualizing training progress and model behavior, and use Vertex AI Feature Store to stove and manage experiment data for analysis and reproducibility.
C. Use Vertex AI Experiments for tracking iterations and comparison, and use Vertex AI TensorBoard for visualization and analysis of the training metrics and model architecture.
D. Use Vertex AI Experiments for tracking iterations and comparison, and use BigQuery and Looker Studio for visualization and analysis of the training metrics and model architecture.
Show Answer
Correct Answer: C
Explanation: Vertex AI Experiments is purpose-built to track experiment runs, hyperparameters, metrics, and compare model iterations. Vertex AI TensorBoard provides rich visualization of training progress, scalars, graphs, embeddings, and model internals, making it the strongest combination for experiment tracking plus deep learning visualization and analysis.
Question 19
You are an enterprise AI architect in a large international company. An ML team has asked you to help with development of a pilot of a customer support bot. The ML team plans to use the DeepSeek-V3.2 model, and they expect a few hundred requests per day. You need to quickly deploy the model using a cost-efficient approach. What should you do?
A. Use the DeepSeek-V3.2 model as a service (MaaS) in Model Garden. Send HTTP requests in the Agent Platform endpoint using the Python requests library.
B. Download the DeepSeek-V3.2 binaries from Model Garden, and deploy the model on a Google Kubernetes Engine (GKE) Autoscaling cluster. Send HTTP requests to the GKE endpoint using the Python requests library.
C. Navigate to the DeepSeek-V3.2 model card in Model Garden. Click “Deploy model” to deploy it as an Agent Platform endpoint. Invoke the endpoint using the aiplatform SDK.
D. Use the DeepSeek-V3.2 model as a service (MaaS) in Model Garden. Use a Python client from the openai SDK, and pass a custom endpoint URL to the client.
Show Answer
Correct Answer: D
Explanation: Use DeepSeek-V3.2 as a managed Model-as-a-Service (MaaS) offering in Model Garden and call it through the OpenAI-compatible Python SDK with the custom endpoint URL. This is the quickest, cost-efficient option for a pilot with a few hundred requests per day because it avoids provisioning and managing a dedicated model deployment or GKE cluster.
Question 20
You have a high-traffic ecommerce application that uses a recommendation model deployed on an Agent Platform endpoint. During flash sales, traffic quickly spikes from 1,000 to 50,000 queries per second (QPS). During these spikes, the application returns 503: Service Unavailable errors because the autoscaler cannot provision new resources quickly enough to meet the sudden demand. Your need to eliminate service disruptions during the start of the sale. How should you configure the endpoint?
A. Change the machine type to an a2-highgpu-1g instance with an NVIDIA A100 GPU.
B. Increase the min_replica_count to a baseline that covers a significant portion of the expected spike, and set the max_replica_count to 100.
C. Set the min_replica_count to 1 and the max_replica_count to 100 in the deployed model’s automatic scaling configuration.
D. Deploy the model to a private Agent Platform endpoint, and autoscale based on GPU utilization.
Show Answer
Correct Answer: B
Explanation: Set min_replica_count high enough to keep sufficient capacity warm before the sale begins, so the endpoint can handle the initial surge while autoscaling catches up. A high max_replica_count then allows it to scale further as demand continues. Setting the minimum to 1 leaves the endpoint exposed to the same provisioning delay.
Question 21
You work for a large retailer, and you need to build a model to predict customer chum. The company has a dataset of historical customer data, including customer demographics purchase history, and website activity. You need to create the model in BigQuery ML and thoroughly evaluate its performance. What should you do?
A. Create a linear regression model in BigQuery ML, and register the model in Vertex AI Model Registry. Use Vertex AI to evaluate the model performance.
B. Create a logistic regression model in BigQuery ML, and register the model in Vertex AI Model Registry. Use ML.ARIMA_EVALUATE function to evaluate the model performance.
C. Create a linear regression model in BigQuery ML. Use the ML.EVALUATE function to evaluate the model performance.
D. Create a logistic regression model in BigQuery ML. Use the ML.CONFUSION_MATRIX function to evaluate the model performance.
Show Answer
Correct Answer: D
Explanation: Customer churn prediction is a binary classification problem, so a logistic regression model is appropriate in BigQuery ML. ML.CONFUSION_MATRIX is used to evaluate classification performance by comparing predicted and actual labels. Linear regression is for continuous targets, and ML.ARIMA_EVALUATE is for time-series forecasting, not classification.
Question 21
You lead an ML team at a financial technology company. Your team is building a system to detect potentially fraudulent credit card transactions in real-time. The model must return a prediction with very low latency (under 200ms) to approve or deny the transaction. The system must also scale to handle millions of transactions per day. Your dataset consists of structured, tabular transaction data stored in BigQuery.
Your team is proficient in data science but wants to avoid the complexity of managing and optimizing a real-time model serving infrastructure. What should you do?
A. In an Agent Platform Workbench notebook, build a deep neural network (DNN) using PyTorch. Provision a cluster of GPU-enabled Compute Engine instances, and create an API to serve the model for real-time predictions.
B. Use BigQuery ML to train a boosted tree classification model. Schedule a batch prediction job using the ML.PREDICT function that runs every minute and scores recent transactions.
C. Use Forecasting with Agent Platform AutoML to train a time-series model on the sequence of transactions. Deploy the model as a tabular workflow to predict which future time windows are likely to contain fraudulent activity.
D. Use Agent Platform AutoML to train using your tabular dataset from BigQuery. Deploy the trained model to an Agent Platform endpoint, and integrate the endpoint’s API into your transaction processing application.
Show Answer
Correct Answer: D
Explanation: Train a tabular classification model with AutoML using the BigQuery data, then deploy it to a managed online prediction endpoint. The endpoint handles scalable real-time serving, avoiding the burden of building and operating custom inference infrastructure. Batch scoring in B does not meet per-transaction latency needs, and forecasting in C is not appropriate for transaction-level fraud classification.
Question 22
You are an ML engineer at a bank. The bank's leadership team wants to reduce the number of loan defaults. The bank has labeled historic data about loan defaults stored in BigQuery. You have been asked to use AI to support the loan application process. For compliance reasons, you need to provide explanations for loan rejections. What should you do?
A. Import the historic loan default data into AutoML. Train and deploy a linear regression model to predict default probability. Report the probability of default for each loan application.
B. Create a custom application that uses the Gemini large language model (LLM). Provide the historic data as context to the model, and prompt the model to predict customer defaults. Report the prediction and explanation provided by the LLM for each loan application.
C. Train and deploy a BigQuery ML classification model trained on historic loan default data. Enable feature-based explanations for each prediction. Report the prediction, probability of default, and feature attributions for each loan application.
D. Load the historic loan default data into a Vertex AI Workbench instance. Train a deep learning classification model using TensorFlow to predict loan default. Run inference for each loan application, and report the predictions.
Show Answer
Correct Answer: C
Explanation: A classification model is appropriate for predicting loan default (a binary outcome), and BigQuery ML can train directly on BigQuery data while supporting feature-based explanations (feature attributions) for individual predictions, which helps satisfy compliance requirements. Option A incorrectly uses linear regression for a classification problem, B relies on an LLM rather than supervised predictive modeling for structured labeled data, and D does not address the requirement to provide explanations.
$19
Get all 367 questions with detailed answers and explanations
Instant download HTML + PDF delivered the moment payment clears.
Secure Stripe checkout we never see or store your card details.
7-day refund if files are defective see our refund policy.