PMLE Architecting Low-Code ML Solutions Practice Question

A retail company wants to build a demand forecasting model for thousands of product SKUs. They have historical sales data in BigQuery and limited ML expertise. They want to minimize coding and automatically handle seasonality and promotions. Which approach should they use?

⚠ Common exam trap

The trap here is assuming that any BigQuery ML model can handle time series seasonality, when only specialized model types like ARIMA_PLUS provide that capability out of the box.

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

✓

Use BigQuery ML with the ARIMA_PLUS model type and provide the time series data.

BigQuery ML's ARIMA_PLUS is purpose-built for time series forecasting and automatically addresses seasonality, holidays, and outliers without manual feature engineering. It operates entirely within BigQuery using SQL, aligning with the team's limited ML expertise and desire to minimize coding. It scales to many time series, making it suitable for thousands of SKUs.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Use BigQuery ML with the ARIMA_PLUS model type and provide the time series data.
Why this is correct
BigQuery ML's ARIMA_PLUS is designed for univariate time series forecasting and automatically handles seasonality, holiday effects, and outliers. It requires only SQL, making it ideal for teams with limited ML expertise. It also supports large-scale training across many time series, such as product SKUs, and can incorporate covariates like promotions. This directly meets the company's need for minimal coding and automatic seasonality handling.
✗
Use Dataflow to preprocess the data and then train a custom TensorFlow model on Vertex AI.
Why it's wrong here
Building a custom TensorFlow model on Vertex AI requires substantial ML expertise and coding, which contradicts the goal of minimizing coding. Dataflow preprocessing adds further development overhead. While this approach offers maximum flexibility, it is not low-code and would take longer to implement. It is overkill for demand forecasting when a specialized BigQuery ML model exists.
✗
Use BigQuery ML with the LINEAR_REG model type and include date features.
Why it's wrong here
LINEAR_REG is a general linear regression model and does not inherently handle time series seasonality or temporal dependencies. Manually engineering date features such as month or day-of-week is possible but does not capture complex seasonal patterns or trends automatically. This approach requires significant feature engineering and may not produce accurate forecasts, failing the requirement for automatic seasonality handling.
✗
Use Vertex AI AutoML Forecasting with the sales data exported to Cloud Storage.
Why it's wrong here
Vertex AI AutoML Forecasting is a viable option but requires exporting data from BigQuery, setting up a dataset in Vertex AI, and managing training and deployment, which adds complexity. While it automates model selection, it does not allow the same SQL-centric workflow and may not scale as seamlessly to thousands of SKUs. The requirement to minimize coding and handle seasonality is better met by a BigQuery ML native model.

Go deeper

PMLE Architecting Low-Code ML Solutions Practice Question

Why each option matters

Option-by-option breakdown

Related to this question