Question 10
Domain 1Your client has a large e-commerce Website that sells sports goods and especially scuba diving equipment. It has a seasonal business and has collected many sales data from its structured ERP and market trend databases. It wants to predict the demand of its customers both to increase business and improve logistics processes. Which of the following types of models and techniques should you focus on to obtain results quickly and with minimum effort?
Correct answer: B
Explanation
BigQuery ML ARIMA fits because the business has structured sales and trend data and needs fast demand forecasting with minimal effort. ARIMA is a time-series model for seasonal patterns, and BigQuery ML lets you train it directly in SQL, so you can “obtain results quickly and with minimum effort.”
Why each option is right or wrong
A. Custom TensorFlow model with an autoencoder neural network
B. BigQuery ML ARIMA
BigQuery ML’s ARIMA_PLUS family is the right fit here because it is a built-in time-series forecasting model in BigQuery ML, trained directly with SQL via CREATE MODEL, so there is no separate ML pipeline to assemble. In the BigQuery ML documentation, ARIMA is specifically intended for forecasting from historical, regularly ordered data and supports seasonal patterns and automatic model selection, which matches the client’s structured ERP and market-trend tables and the need for rapid demand prediction with minimal engineering effort.
C. BigQuery Boosted Tree.
D. BigQuery Linear regression