hardMultiple Choice
PMLE Practice Question: A global e-commerce company uses BigQuery ML to…
A global e-commerce company uses BigQuery ML to forecast daily sales for 10,000 products. They use a time-series model with a horizon of 7 days. Recently, forecasts for a specific product category have been consistently too high. They suspect the model is not capturing a new seasonal pattern. Which action should they take first to diagnose the issue?
⚠ Common exam trap
Google Cloud often tests the principle that diagnosis must precede action—candidates mistakenly jump to retraining or switching tools instead of evaluating the existing model's performance on the problematic data window.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Run ML.EVALUATE on the recent sales data and compare accuracy metrics
Running ML.EVALUATE on recent sales data allows you to compute accuracy metrics (e.g., MAE, MAPE) specifically for the period where the model is failing. This isolates whether the error is due to a new seasonal pattern or another cause, without retraining or changing the model architecture. It is the standard first diagnostic step in BigQuery ML for time-series models.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Retrain the model with minimal additional data
Why it's wrong here
Retraining with minimal additional data alters the model before the cause is known, and a small sample cannot confirm a new seasonal pattern. The option tempts because retraining is the eventual fix, but diagnosis first requires examining residuals and seasonality in the existing training data.
- ✓
Run ML.EVALUATE on the recent sales data and compare accuracy metrics
Why this is correct
ML.EVALUATE computes accuracy metrics such as MAE and RMSE against recent labelled sales, revealing whether the systematic over-prediction stems from the model failing to capture the new seasonal pattern before any retraining or feature changes are attempted.
- ✗
Increase the forecast horizon to 14 days
Why it's wrong here
Extending the horizon to 14 days changes how far ahead predictions run, not why a 7-day forecast is biased high. Diagnosis requires inspecting the training data and residuals for the affected category. Longer horizons suit planning further ahead, not investigating systematic over-forecasting.
- ✗
Switch to AutoML forecasting via Vertex AI AutoML
Why it's wrong here
Switching to AutoML forecasting via Vertex AI AutoML would introduce a full automated model search, which is a heavier, slower diagnostic step than inspecting the existing BigQuery ML model’s seasonal components. The temptation arises because Vertex AI AutoML excels at handling complex, non-linear patterns without manual feature engineering, and it would be the correct choice if the team needed to replace the current model entirely after confirming the seasonal failure. However, the immediate diagnostic need is to examine the model’s captured seasonality, not to deploy a different modelling paradigm.
Go deeper
Related to this question
About these practice questions
This PMLE question is part of Courseiva's 775-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This PMLE practice question is part of Courseiva's free Google Cloud certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the PMLE exam.