Medium — PMLE Practice Quiz

Question 1

A retail chain wants to classify products on store shelves using cameras that operate in stores with unreliable internet connectivity. The data science team has limited ML coding experience but has thousands of labeled product images. They need a solution that trains a custom image classifier and can run inference directly on in-store edge devices without a constant network connection. Which approach best meets these requirements?

Accepted Answer

Train a custom model with Vertex AI AutoML Image Classification using the 'Edge' model type, then export the model to run on the in-store devices.

Answer

Use the Cloud Vision API label detection endpoint from each in-store device to classify products in real time.

Answer

Train a Vertex AI AutoML Image Classification model with the 'Cloud' hosted model type and call its online prediction endpoint from the devices.

Answer

Build a custom TensorFlow CNN in Vertex AI Workbench notebooks and containerize it for edge deployment.

Question 2

A fintech company wants to build a binary classification model in Vertex AI AutoML Tabular to detect fraudulent transactions. Only 0.8% of the labeled transactions are fraudulent. The team's priority is to catch as many actual fraud cases as possible while keeping false positives at a manageable level, and they have limited ML expertise. Which approach should they configure to best meet this goal?

Accepted Answer

Train the AutoML Tabular model and set the optimization objective to maximize the area under the precision-recall curve (AU PRC).

Answer

Train the AutoML Tabular model with the default optimization objective of maximizing the area under the ROC curve (AU ROC).

Answer

Manually downsample the majority class to a 50/50 balance before training and optimize for overall accuracy.

Answer

Switch to a BigQuery ML logistic regression model and optimize for log loss since AutoML cannot handle imbalanced data.

Question 3

A logistics company wants to predict package delivery times using a structured dataset in Vertex AI. The data science team has limited coding experience and needs a solution that requires minimal ML expertise. Business stakeholders also require the model to report which features most influence each individual prediction, and the model must be queried in real time from a customer-facing web application. Which approach best meets all requirements?

Accepted Answer

Train an AutoML tabular regression model in Vertex AI, deploy it to an online endpoint, and enable Vertex Explainable AI feature attributions on the predictions.

Answer

Train a custom TensorFlow regression model with a hand-written training loop and serve it via a Compute Engine VM.

Answer

Train an AutoML tabular regression model in Vertex AI and use only batch prediction jobs to generate delivery time estimates.

Answer

Use BigQuery ML to train a linear regression model and export it to a TensorFlow SavedModel for local inference.

Question 4

A marketing analytics team with limited ML expertise wants to build a churn prediction model from a customer table already in BigQuery. They choose Vertex AI AutoML Tabular through the console. During job configuration, they must set a training budget expressed in node hours. They ask you how this setting affects the outcome and how to choose a reasonable value for their first experiment. What is the most accurate guidance?

Accepted Answer

The budget caps the maximum compute AutoML spends searching architectures and tuning; AutoML may stop early if the model converges, and a small budget is appropriate for an initial baseline experiment.

Answer

The budget sets the number of prediction nodes for the deployed endpoint, so it should match expected serving traffic rather than training needs.

Answer

The budget determines how many rows of the dataset AutoML uses for training, so a higher budget always means more data is included.

Answer

The budget is a hard minimum runtime; AutoML will always consume the entire allocation even if the model has already converged, so it should be set as low as possible to save money.

Question 5

A sports media company wants to automatically tag short game clips with the specific athletic actions they contain (e.g., 'shot on goal', 'free kick', 'tackle') along with the time segments where each action occurs. The data science team has only a few weeks, limited ML expertise, and a labeled dataset of a few thousand video clips. They want the lowest-code approach on Google Cloud that produces temporal action segments. Which solution best fits these requirements?

Accepted Answer

Use AutoML (Vertex AI) to train an action recognition video model on the labeled clips

Answer

Use the Vision API's label detection endpoint on sampled frames from each clip

Answer

Write a custom PyTorch 3D-CNN training job on Vertex AI custom training with a GPU cluster

Answer

Use the Video Intelligence API's prebuilt label detection to identify actions

Question 6

A retail analytics team needs to score 400 million customer records once per week using a trained TensorFlow model deployed on Vertex AI. The records live in a large BigQuery table. Latency is not a concern, but the team wants the job to complete as quickly and cheaply as possible while avoiding the operational overhead of managing infrastructure. Which approach best meets these requirements?

Accepted Answer

Run a Vertex AI batch prediction job that reads directly from the BigQuery table as the input source and writes results back to BigQuery, letting the service distribute the workload.

Answer

Deploy the model to a Vertex AI online endpoint with autoscaling and send the 400 million records as individual prediction requests from a Dataflow job.

Answer

Export the BigQuery table to a single large CSV file in Cloud Storage and run a batch prediction job pointed at that file.

Answer

Provision a large GPU-backed Compute Engine VM, load the model, and iterate through the records with a custom Python loop.

Question 7

A retail analytics team needs to score their entire customer base (about 40 million records) once every night to generate propensity scores for a next-day marketing campaign. The scores are consumed by a downstream BigQuery table the following morning, so end-to-end latency of a few hours is acceptable. The team currently keeps a Vertex AI online endpoint with multiple GPU replicas running 24/7 to handle this workload, but finance has flagged the cost as excessive. What is the most appropriate change to reduce cost while meeting requirements?

Accepted Answer

Switch to a Vertex AI batch prediction job that reads from BigQuery, runs on demand each night, and provisions compute only for the duration of the job.

Answer

Keep the online endpoint but reduce it to a single CPU replica and disable autoscaling to lower hourly cost.

Answer

Keep the online endpoint but enable dynamic request batching to increase throughput per replica.

Answer

Deploy the model to a private endpoint inside the VPC to reduce network egress charges during scoring.

Question 8

Your team maintains a fraud-scoring model deployed on a Vertex AI online endpoint. A new business requirement asks you to re-score the entire historical transaction table (2 billion rows) once, to backfill risk labels for an analytics dashboard. There is no latency requirement for this one-time job, but you want to minimize cost and total wall-clock time. The online endpoint currently autoscales between 3 and 10 GPU replicas. What is the most appropriate approach?

Accepted Answer

Run a Vertex AI batch prediction job that reads the table from BigQuery, using a high machine count to parallelize the workload.

Answer

Send the 2 billion rows to the existing online endpoint by fanning out many concurrent HTTP requests and temporarily raising max replicas to 50.

Answer

Deploy a second online endpoint dedicated to the backfill and stream all rows through it with dynamic batching enabled.

Answer

Export the online endpoint model and run inference locally in a single notebook loop over all 2 billion rows.

Question 9

A data science team prototypes models in a Vertex AI Workbench notebook using a 50 GB sample pulled into a Pandas DataFrame. The full training dataset lives in BigQuery and is roughly 8 TB, requiring complex windowed aggregations and joins across several tables. The team wants a preprocessing approach that scales to the full dataset for production training runs, minimizes custom infrastructure management, and produces feature tables that both training and future batch jobs can reuse. Which approach should they adopt?

Accepted Answer

Perform the set-based aggregations and joins directly in BigQuery using SQL, materializing the results into curated feature tables that downstream jobs query.

Answer

Increase the notebook machine to a high-memory instance and continue running the transformations with Pandas on the full 8 TB dataset.

Answer

Export the BigQuery tables to CSV files in Cloud Storage and process them with a manually configured Dataproc cluster running Spark.

Answer

Load the full dataset into the notebook in chunks and loop over each chunk with scikit-learn preprocessing transformers.

Question 10

A data science team prototypes models in Vertex AI Workbench notebooks. Their preprocessing code uses pandas to read and transform a 400 GB BigQuery table, but the notebook kernel repeatedly crashes with out-of-memory errors. The team wants to keep writing familiar pandas-style code in the notebook while pushing the heavy computation down to BigQuery so the data never has to fit in the notebook's memory. What should they do?

Accepted Answer

Use the BigQuery DataFrames (bigframes) library, which exposes a pandas-compatible API but executes operations as BigQuery SQL on the server side.

Answer

Increase the Workbench instance to the largest available machine type with more RAM and continue using pandas with the BigQuery client.

Answer

Export the BigQuery table to CSV files in Cloud Storage and read them into pandas in chunks with the chunksize parameter.

Answer

Load the table into a Vertex AI Feature Store and read features into a pandas DataFrame for preprocessing.

Question 11

A data science team at a logistics company needs to explore three years of shipment event logs stored as newline-delimited JSON files in a Cloud Storage bucket (roughly 40 TB, organized in Hive-style date directories like /year=2023/month=05/). Analysts want to run ad hoc exploratory SQL in BigQuery to profile the data before committing to any modeling approach, but leadership is worried about query costs and does not want to duplicate the raw data into BigQuery-managed storage yet. Which approach best supports low-cost, iterative exploration?

Accepted Answer

Create a BigQuery external table over the Cloud Storage files with Hive partitioning enabled, and have analysts filter on the partition columns in their exploratory queries.

Answer

Load all 40 TB into a native BigQuery table with ingestion-time partitioning so analysts can query without touching Cloud Storage.

Answer

Create a non-partitioned external table over the JSON files and instruct analysts to add LIMIT clauses to reduce the amount of data scanned.

Answer

Use a Dataflow pipeline to convert the JSON to Parquet in Cloud Storage first, then query each file individually through the BigQuery Storage Read API.

Question 12

A retail analytics team stores all their customer transaction data in BigQuery. They want to build a churn prediction model directly in BigQuery ML using a boosted tree classifier, and they want BigQuery ML to automatically search for the best combination of learning rate and max tree depth rather than manually experimenting. They also need the final model to be usable for online predictions from a Vertex AI endpoint later. Which approach best meets these requirements with the least custom code?

Accepted Answer

Create a BOOSTED_TREE_CLASSIFIER model in BigQuery ML with NUM_TRIALS and HPARAM_RANGE/HPARAM_CANDIDATES options to enable hyperparameter tuning, then export the model and register it to Vertex AI for online serving.

Answer

Train a custom XGBoost model in a Vertex AI custom training job, manually tune hyperparameters with Vertex AI Vizier, then deploy to an endpoint.

Answer

Use AutoML Tables in Vertex AI, which handles hyperparameter tuning automatically, and skip BigQuery ML entirely.

Answer

Create a LOGISTIC_REG model in BigQuery ML with L1_REG and L2_REG regularization options, since boosted trees do not support hyperparameter tuning in BigQuery ML.

Question 13

A retail analytics team stores three years of daily sales transactions in BigQuery. They need to produce a 30-day demand forecast for each of 5,000 products, including confidence intervals, while keeping the data in place and minimizing custom code or infrastructure management. Which approach best meets these requirements?

Accepted Answer

Create a BigQuery ML ARIMA_PLUS model with a time-series column, item identifier, and TIME_SERIES_ID_COL to train per-product models, then use ML.FORECAST to generate predictions with prediction intervals.

Answer

Export the sales data to Cloud Storage, train a custom LSTM model on Vertex AI with a TensorFlow container, and deploy it to an endpoint for batch forecasting.

Answer

Use a BigQuery ML LINEAR_REG model with the date as a numeric feature and call ML.PREDICT to estimate future sales for each product.

Answer

Send each product's historical sales to the Vertex AI Gemini API and prompt the model to predict the next 30 days of demand.

Question 14

A retail analytics team has a BigQuery table with millions of rows of customer transaction data, including recency, frequency, and monetary value features. The marketing department wants to group customers into an unspecified number of natural segments for targeted campaigns, but there are no pre-existing labels indicating which segment each customer belongs to. The team wants a fully SQL-based, low-code approach without exporting data. Which BigQuery ML approach should they use?

Accepted Answer

Create a k-means model using CREATE MODEL with MODEL_TYPE='KMEANS' and evaluate cluster quality with the Davies-Bouldin index

Answer

Create a logistic regression model using MODEL_TYPE='LOGISTIC_REG' to predict each customer's segment label

Answer

Create a multiclass classification model using MODEL_TYPE='DNN_CLASSIFIER' on the transaction features

Answer

Create an ARIMA_PLUS time-series model to forecast future customer purchasing behavior

Question 15

A retail analytics team has trained a logistic regression model in BigQuery ML to predict which customers will churn. Business stakeholders want to understand, for each individual prediction, which features pushed the customer toward or away from churning so they can design targeted retention offers. The team wants to stay entirely within BigQuery using SQL and avoid exporting the model. Which approach should they use?

Accepted Answer

Run ML.EXPLAIN_PREDICT on the model to obtain per-prediction feature attributions alongside the predicted labels

Answer

Run ML.GLOBAL_EXPLAIN after enabling global explanations during training to see per-customer feature contributions

Answer

Run ML.EVALUATE to produce a confusion matrix and precision/recall values for each customer

Answer

Export the model to Vertex AI and enable Vertex Explainable AI with sampled Shapley to get per-row attributions

Question 16

A retail analytics team stores millions of transaction records in BigQuery. A data scientist has already trained and deployed a custom fraud-scoring model to a Vertex AI online endpoint. The business analysts, who only know SQL, need to run predictions against this deployed model directly from their BigQuery queries without exporting data or writing Python. Which approach best meets this requirement with the least operational overhead?

Accepted Answer

Create a BigQuery ML remote model referencing the Vertex AI endpoint, then call ML.PREDICT on it from SQL.

Answer

Export the BigQuery table to Cloud Storage and run a Vertex AI batch prediction job against the endpoint.

Answer

Re-train the fraud model entirely inside BigQuery ML using CREATE MODEL so the analysts can use ML.PREDICT.

Answer

Have the analysts call the Vertex AI endpoint through a Cloud Function that they invoke via HTTP for each row.

Question 17

A retail analytics team stores millions of customer feedback comments in a BigQuery table. Analysts who know SQL but have no ML or Python experience want to classify each comment into one of five predefined product-category themes and generate a one-sentence summary, running the process entirely within their existing BigQuery workflows. They want the fastest path to production without training a custom model or standing up separate inference infrastructure. What should they do?

Accepted Answer

Create a BigQuery ML remote model that references a Vertex AI Gemini endpoint, then call ML.GENERATE_TEXT with a prompt column that instructs the model to classify and summarize each comment.

Answer

Export the comments to Cloud Storage, train an AutoML text classification model in Vertex AI, deploy it to an online endpoint, and call it from a scheduled query.

Answer

Use CREATE MODEL with model_type='logistic_reg' in BigQuery ML to train a multiclass classifier directly on the raw comment text.

Answer

Build a Vertex AI Pipeline that reads from BigQuery, fine-tunes a foundation model on the comments, and writes predictions back to a results table.

Question 18

A retail analytics team stores millions of product reviews in a BigQuery table. Analysts who are comfortable with SQL but not with Python want to generate concise one-sentence summaries of each review directly inside their existing BigQuery workflow, without building a custom pipeline or managing serving infrastructure. Which approach best meets these requirements with the least operational overhead?

Accepted Answer

Create a BigQuery ML remote model that references a Vertex AI Gemini endpoint, then call ML.GENERATE_TEXT in a SQL query over the reviews table.

Answer

Export the reviews to Cloud Storage, run a Vertex AI batch prediction job against a Gemini model, and load the summaries back into BigQuery.

Answer

Train a custom text summarization model with AutoML and deploy it to a Vertex AI online endpoint that analysts query via the REST API.

Answer

Build a Dataflow streaming pipeline that reads from BigQuery, calls the Vertex AI SDK for each row, and writes summaries to a new table.

Question 19

A data analytics team wants to run entity sentiment analysis on millions of product reviews stored in a BigQuery table. They prefer to stay entirely within SQL and avoid writing any Python or exporting data. They plan to use the Cloud Natural Language API via BigQuery ML. When creating the remote model with CREATE MODEL ... REMOTE WITH CONNECTION, what is the essential configuration step required so that BigQuery can successfully invoke the Cloud Natural Language API?

Accepted Answer

Grant the BigQuery connection's service account the appropriate IAM role (e.g., Cloud Natural Language API user/service usage) and enable the Cloud Natural Language API in the project

Answer

Export the reviews to Cloud Storage first, because BigQuery ML remote models can only read input from GCS buckets

Answer

Deploy the Natural Language model to a Vertex AI endpoint and reference that endpoint URL in the ENDPOINT option of the remote model

Answer

Create a service account key file and embed the JSON credentials directly in the SQL CREATE MODEL statement

Question 20

A data analytics team stores millions of customer review texts in a BigQuery table. They want to build a semantic search feature that finds reviews similar to a given query, and they prefer to stay entirely within SQL workflows without exporting data or writing Python pipelines. They need to generate text embeddings at scale directly in BigQuery. What is the most appropriate low-code approach?

Accepted Answer

Create a BigQuery ML remote model that references a Vertex AI text embedding foundation model, then call ML.GENERATE_EMBEDDING on the reviews table.

Answer

Train an AutoML text classification model in Vertex AI and use its prediction scores as embedding vectors for similarity search.

Answer

Export the reviews to Cloud Storage and call the Natural Language API's entity analysis to compute similarity between documents.

Answer

Use CREATE MODEL with a BigQuery ML matrix factorization model to produce embeddings from the review text columns.

Question 21

A retail analytics team stores 4 million product photos in Cloud Storage, with their metadata (GCS URIs, SKU, category) already loaded into a BigQuery object table. Analysts who are fluent in SQL but have no ML training pipeline experience need to generate descriptive labels for each image to enrich the product catalog. They want the lowest-effort approach that keeps everything within their existing BigQuery workflow and does not require them to build or manage any serving infrastructure. What should they do?

Accepted Answer

Create a BigQuery ML remote model that connects to the Cloud Vision API and call ML.ANNOTATE_IMAGE over the object table to generate labels directly in SQL.

Answer

Train an AutoML image classification model in Vertex AI, deploy it to an online endpoint, and have analysts write SQL that calls the endpoint per row.

Answer

Export all images to a Vertex AI managed dataset, run a custom TensorFlow training job to build a labeler, then batch predict and load results back to BigQuery.

Answer

Write a Dataflow pipeline that reads the object table, calls the Vision API for each image, and streams annotations into a BigQuery results table.

Question 22

A retail analytics team has an existing TensorFlow SavedModel that predicts product return likelihood. The model was trained outside Google Cloud by a data science partner. The team wants their SQL-focused analysts to run batch predictions on customer transaction data that already lives in BigQuery, without exporting the data or standing up a separate serving infrastructure. What is the most appropriate low-code approach?

Accepted Answer

Use CREATE MODEL with the MODEL_TYPE='TENSORFLOW' option and MODEL_PATH pointing to the SavedModel in Cloud Storage, then run ML.PREDICT against the BigQuery table

Answer

Deploy the SavedModel to a Vertex AI endpoint and have analysts call the endpoint from a Cloud Function for each transaction row

Answer

Retrain the model from scratch as a BigQuery ML boosted tree classifier since imported TensorFlow models cannot be used for prediction in BigQuery

Answer

Export the BigQuery table to Cloud Storage as CSV and run the TensorFlow model locally with a Python batch script

Question 23

Your team trains a large PyTorch image model on Vertex AI custom training. Each run takes about 30 hours on a single node with multiple GPUs. To reduce cost, you switched to Spot (preemptible) VMs, but you notice that when a VM is reclaimed, the job restarts from scratch and wastes many GPU-hours. You must keep costs low while ensuring interrupted runs can resume efficiently. What should you do?

Accepted Answer

Periodically save model and optimizer state to Cloud Storage and configure the training job to resume from the latest checkpoint on restart, keeping Spot VMs and enabling automatic retries.

Answer

Switch back to standard (on-demand) VMs and remove checkpointing since the job will no longer be interrupted.

Answer

Reduce the number of training epochs so that each run completes before a Spot VM is likely to be preempted.

Answer

Move the training to a smaller CPU-only machine so that preemption happens less frequently and restarts are cheaper.

Question 24

Your team has prototyped a gradient-boosted decision tree model (XGBoost) on a small tabular dataset for predicting equipment maintenance needs. You now need to scale training to a 200 GB dataset and later serve batch predictions nightly. A junior engineer suggests provisioning a cluster of GPU-accelerated VMs for both training and inference to maximize speed. What is the most cost-effective and appropriate hardware recommendation for this workload?

Accepted Answer

Use high-memory CPU machines for both distributed training and batch inference, since tree-based models like XGBoost are largely CPU-bound and gain little from GPU acceleration relative to cost.

Answer

Use TPUs for training and GPUs for batch inference, because TPUs offer the best price-performance for all tabular model types.

Answer

Use a large fleet of GPU VMs for training and inference to match the engineer's recommendation, as GPUs accelerate all matrix operations regardless of model architecture.

Answer

Use TPU Pods for training because the 200 GB dataset requires the parallelism only TPUs provide, then serve inference on CPUs.

Question 25

Your team deployed a credit-approval model on Vertex AI. Regulators require ongoing evidence that the model does not produce discriminatory outcomes across protected groups such as gender and ethnicity. The model shows strong overall accuracy, but leadership is concerned about fairness in production. Which approach best addresses this responsible-AI risk during ongoing monitoring?

Accepted Answer

Continuously monitor approval rates and error rates disaggregated by protected group using fairness metrics such as demographic parity difference and equal opportunity difference, and alert when disparities exceed defined thresholds.

Answer

Rely on the model's overall accuracy and AUC in production, since a high-performing model is inherently fair across all subgroups.

Answer

Remove the protected attributes from the training features so the model cannot use them, which guarantees the outcomes are unbiased.

Answer

Enable feature-attribution drift monitoring on the input features and treat any drift alert as evidence of a fairness violation.