AWS Certified Machine Learning – Specialty — Question 335

A manufacturing company produces 100 types of steel rods. The rod types have varying material grades and dimensions. The company has sales data for the steel rods for the past 50 years.

A data scientist needs to build a machine learning (ML) model to predict future sales of the steel rods.

Which solution will meet this requirement in the MOST operationally efficient way?

Answer options

• A. Use the Amazon SageMaker DeepAR forecasting algorithm to build a single model for all the products.
• B. Use the Amazon SageMaker DeepAR forecasting algorithm to build separate models for each product.
• C. Use Amazon SageMaker Autopilot to build a single model for all the products.
• D. Use Amazon SageMaker Autopilot to build separate models for each product.

Correct answer: A

Explanation

Amazon SageMaker DeepAR is specifically designed for forecasting time series data and performs exceptionally well when trained on multiple related time series simultaneously, allowing a single model to learn patterns across all 100 products. Building separate models for each product using DeepAR or Autopilot increases operational overhead significantly. Furthermore, SageMaker Autopilot is not optimized for multi-series forecasting tasks compared to DeepAR, which natively handles cross-series relationships and cold-start scenarios.