Answer-first summary for fast verification
Answer: Use BigQuery ML to build a statistical ARIMA_PLUS model.
The correct answer is C: Use BigQuery ML to build a statistical ARIMA_PLUS model. This approach is optimal for several reasons: it ensures quick implementation because BigQuery ML simplifies the model training and deployment process without needing to move data or set up complex environments. Additionally, ARIMA_PLUS is a pre-built statistical model tailored for time series forecasting, making it an ideal choice for monthly sales predictions. This solution requires minimal effort compared to building custom models using Prophet, Vertex AI Forecast, or TensorFlow, which would involve significant coding, setup, and expertise.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You work as a data scientist for an online retailer with a few thousand short lifecycle products, such as seasonal or limited edition items. Over the past 5 years, your company has accumulated a substantial amount of sales data, which is stored in BigQuery. Your task is to develop a model that will predict monthly sales for each product with the primary objective of implementing a solution quickly and with minimal effort. Considering the available tools and the nature of the data, what approach should you take?
A
Use Prophet on Vertex AI Training to build a custom model.
B
Use Vertex AI Forecast to build a NN-based model.
C
Use BigQuery ML to build a statistical ARIMA_PLUS model.
D
Use TensorFlow on Vertex AI Training to build a custom model.
No comments yet.