PMLE Architecting Low-Code ML Solutions Practice Question

A retail company wants to forecast daily sales for the next 30 days based on historical sales data. They have two years of daily sales records with no missing values. They want to use a low-code solution on Google Cloud that automatically handles seasonality and trends. Which service should they use?

⚠ Common exam trap

A common mix-up: candidates confuse general-purpose regression models with specialized time series models, overlooking that only ARIMA_PLUS automatically handles temporal patterns like seasonality.

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

✓

BigQuery ML with the ARIMA_PLUS model

BigQuery ML's ARIMA_PLUS is the correct choice because it is a low-code, SQL-based time series forecasting model that automatically handles seasonality, trends, and holidays. It is designed for exactly this type of scenario: forecasting future values from historical time series data. Other options either require manual feature engineering, are not forecasting-specific, or involve significant coding, making ARIMA_PLUS the most efficient and appropriate solution.

Answer analysis

Option-by-option breakdown

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

✗
Cloud Dataflow with a sliding window aggregation
Why it's wrong here
Cloud Dataflow is a data processing service, not a forecasting tool. While you could compute sliding window aggregates, it would not produce a predictive model or forecasts. It would require additional ML libraries and coding to build a forecasting solution, which is not low-code. Dataflow is better suited for data pipelines, not for generating time series predictions directly.
✗
Vertex AI Forecasting with a custom training container
Why it's wrong here
Vertex AI Forecasting is not a standalone service; forecasting typically requires building a custom model or using AutoMLForecasting, which is not mentioned. A custom training container would involve significant coding and ML expertise, contradicting the low-code requirement. The scenario explicitly asks for a low-code solution, so a custom container is overkill and not the intended approach.
✓
BigQuery ML with the ARIMA_PLUS model
Why this is correct
BigQuery ML's ARIMA_PLUS model is specifically designed for time series forecasting. It automatically handles seasonality, trends, and holiday effects, and can generate forecasts for multiple time steps. It requires only SQL to train and predict, making it a low-code solution. Given the clean daily sales data, ARIMA_PLUS is well-suited to produce accurate 30-day forecasts without manual feature engineering.
✗
AutoML Tables with a regression target
Why it's wrong here
AutoML Tables is designed for tabular data but does not natively handle time series forecasting with temporal dependencies. While you could create lag features manually, it would not automatically account for seasonality and trends. The scenario requires automatic handling of these time series characteristics, which AutoML Tables does not provide out of the box, making it less suitable than a dedicated time series model.

Go deeper

PMLE Architecting Low-Code ML Solutions Practice Question

Why each option matters

Option-by-option breakdown

Related to this question