PMLE Solving business challenges with ML — Timed 10 Questions

Question 1

A retail company wants to forecast weekly sales for each of its 500 stores. The data includes historical sales, promotions, holidays, and local weather. The company needs to update forecasts every week with new data. Which ML approach should they use?

Accepted Answer

Use Vertex AI Forecasting to train a time-series model with holiday and weather features. Vertex AI Forecasting is purpose-built for time-series forecasting with support for exogenous features like holidays and weather, making it the ideal choice for weekly sales predictions across 500 stores. It handles multiple time series automatically and integrates with the required weekly retraining cycle, unlike generic regression models that lack temporal awareness.

Answer

Use BigQuery ML to create a linear regression model on historical data

Answer

Export data to AutoML Tables and train a regression model

Answer

Build a custom LSTM model using TensorFlow on Vertex AI Workbench

Question 2

A media company uses a custom Python script on a Compute Engine VM to run batch predictions with a large ML model. The script loads the model from Cloud Storage, processes records from a Pub/Sub pull subscription, and writes results to BigQuery. Predictions are taking too long and the VM often runs out of memory. Which two changes should the company implement to improve performance and scalability? (Choose TWO)

Accepted Answer

Change Pub/Sub to a push subscription that sends messages to a load-balanced group of VMs. Option B is correct because switching to a push subscription with a load-balanced group of VMs distributes the message processing load across multiple instances, preventing any single VM from being overwhelmed. This directly addresses the memory exhaustion issue by parallelizing the work and allowing horizontal scaling.

Answer

Deploy the model on Vertex AI Prediction for batch prediction

Answer

Switch to a larger VM with more memory

Answer

Store results in Cloud SQL instead of BigQuery

Question 3

A hospital wants to deploy a machine learning model for detecting anomalies in patient vital signs. The model was trained on historical data but must comply with HIPAA regulations. The model serving must be low-latency (under 100 ms) and handle up to 1000 requests per second. Which architecture should they use on Google Cloud?

Accepted Answer

Deploy the model to Vertex AI Prediction with a private endpoint and use VPC Service Controls for data isolation. Vertex AI Prediction with a private endpoint and VPC Service Controls meets all requirements: it provides low-latency (sub-100ms) online predictions for up to 1000 QPS, enforces HIPAA compliance by isolating the model within a VPC and preventing data exfiltration, and supports autoscaling. Batch Prediction (A) cannot meet the latency requirement, BigQuery ML (B) is designed for analytical queries not real-time serving, and Cloud Run (C) lacks native HIPAA-compliant data isolation controls.

Answer

Use Vertex AI Batch Prediction to run predictions in batch jobs every hour

Answer

Use BigQuery ML to run predictions directly from a BigQuery table

Answer

Deploy the model as a container on Cloud Run with a load balancer

Question 4

A data scientist deployed a TensorFlow model for sentiment analysis to Vertex AI Prediction. The model expects input key 'text' but the client sends requests with key 'review_text'. Which step should the data scientist take to resolve the error without retraining the model?

Accepted Answer

Modify the client code to send requests with input key 'text'. Option D is correct because the most straightforward and reliable solution is to modify the client code to send the request with the expected input key 'text'. This avoids any additional infrastructure, latency, or complexity, and does not require retraining the model or altering the deployed endpoint. Vertex AI Prediction serves the model as-is, so aligning the client's request format with the model's expected input is the simplest and most maintainable fix.

Answer

Use a Cloud Function to strip the 'review_text' key and replace it with 'text'

Answer

Retrain the model with input key 'review_text'

Answer

Create a new Vertex AI Endpoint with an alias mapping 'review_text' to 'text'

Question 5

A logistics company uses a regression model to predict delivery times. The model currently uses features: distance (km), traffic index, weather condition, and time of day. The data scientist notices that the model's predictions are systematically too low for deliveries during peak traffic hours. Which action would best address this issue?

Accepted Answer

Add a cross-feature that multiplies distance by traffic index. The model's systematic underestimation during peak traffic hours indicates a missing interaction effect between distance and traffic. Adding a cross-feature (distance × traffic index) allows a linear model to capture the non-linear relationship where traffic disproportionately increases delivery time over longer distances. This directly addresses the bias without discarding useful data or unnecessarily complicating the model.

Answer

Switch to a deep neural network model

Answer

Remove the traffic index feature as it is causing bias

Answer

Collect more training data during peak traffic hours

Question 6

An e-commerce company uses a recommendation model that suggests products based on user browsing history. The model was trained on data from the past year and has high accuracy on the test set. However, after deployment, the click-through rate (CTR) on recommendations is much lower than expected. Which three steps should the data scientist take to diagnose and improve the model? (Choose THREE)

Accepted Answer

Set up an A/B experiment comparing the model's recommendations against a baseline. Option B is correct because an A/B experiment directly measures the model's real-world impact by comparing its CTR against a baseline (e.g., random or popularity-based recommendations). This isolates the model's performance from confounding factors like seasonality or user behavior changes, providing a causal estimate of its effectiveness.

Answer

Run offline evaluation on a holdout dataset to confirm accuracy

Answer

Increase the training dataset size by including data from two years ago

Question 7

A data scientist runs a BigQuery ML prediction query and gets a region mismatch error. The model is in the US region, but the new_data table is in the EU region. What is the simplest way to resolve this?

Accepted Answer

Copy the new_data table to the US region using the BigQuery UI or CLI. Option B is correct because the simplest fix is to move the new_data table to the same region as the model (US). BigQuery ML requires that the model and the data used for predictions reside in the same multi-region or regional location. Copying the table via the BigQuery UI or CLI (e.g., `bq cp`) is a straightforward, no-code operation that avoids retraining or exporting the model.

Answer

Recreate the model in the EU region using the same training data

Answer

Enable cross-region query in BigQuery settings

Answer

Export the model from US and import it to EU

Question 8

A financial services company wants to detect fraudulent transactions in real-time. They have a trained XGBoost model that runs on a single Compute Engine instance. The current solution processes about 100 transactions per second, but they need to scale to 10,000 transactions per second. Which approach should they take?

Accepted Answer

Deploy the model to Vertex AI Prediction with autoscaling enabled. Vertex AI Prediction with autoscaling is the correct choice because it is purpose-built for serving ML models at scale, automatically adjusting the number of compute nodes based on incoming request traffic. This allows the company to seamlessly handle the increase from 100 to 10,000 transactions per second without manual intervention, while XGBoost is natively supported as a framework.

Answer

Increase the VM to a machine type with more vCPUs and memory

Answer

Use Dataflow to process transactions in micro-batches every second

Answer

Rewrite the model as a Cloud Function triggered by Pub/Sub messages

Question 9

A manufacturing company wants to predict equipment failure using sensor data. The data is highly imbalanced (only 1% failures). They are using a gradient boosted tree model with class weights. The model achieves 0.99 recall but 0.2 precision on the test set. Which two actions should they take to improve precision without significantly hurting recall? (Choose TWO)

Accepted Answer

Try an anomaly detection algorithm like Isolation Forest. Option B is correct because anomaly detection algorithms like Isolation Forest are designed to identify rare events by isolating anomalies rather than modeling the majority class, which can improve precision when the minority class is extremely rare (1%). Option E is correct because increasing the decision threshold for classifying a positive reduces false positives by requiring higher confidence for a positive prediction, directly improving precision while only minimally reducing recall if the model's probability scores are well-calibrated.

Answer

Oversample the minority class using SMOTE

Answer

Add more features to the model

Answer

Increase the class weight for the minority class

Question 10

A healthcare startup is building a diagnostic tool that uses a deep learning model to classify medical images. The model is trained on TensorFlow and deployed on Vertex AI Prediction. The startup has strict latency requirements: predictions must return within 200 ms for 95% of requests. Current performance shows p95 latency of 350 ms. The team has already tried using a smaller model, but accuracy dropped below acceptable levels. The traffic pattern is spiky: low load during nights but bursts of 1000 requests per second during business hours. Currently, they use a single n1-highmem-8 VM with a GPU attached. They have a budget for additional resources but need to optimize cost. The model is about 500 MB and requires GPU for inference. Which course of action should they take to meet the latency requirement while managing costs?

Accepted Answer

Create a Vertex AI Prediction endpoint with an accelerator (GPU) and enable autoscaling (min 1, max 5 nodes). Option C is correct because it leverages Vertex AI Prediction's autoscaling to handle spiky traffic efficiently, using GPU-accelerated endpoints that can scale from 1 to 5 nodes to meet the 200 ms p95 latency requirement. This approach minimizes cost during low-load periods while providing burst capacity for the 1000 requests per second peak, addressing both the latency and budget constraints without compromising model accuracy.

Answer

Upgrade to an n1-highmem-16 VM with a more powerful GPU

Answer

Switch to batch prediction using Vertex AI Batch Prediction and store results in a database for retrieval

Answer

Deploy the model as a Cloud Function using TensorFlow Serving