AWS Certified Machine Learning – Specialty — Question 259

A financial company sends special offers to customers through weekly email campaigns. A bulk email marketing system takes the list of email addresses as an input and sends the marketing campaign messages in batches. Few customers use the offers from the campaign messages. The company does not want to send irrelevant offers to customers.

A machine learning (ML) team at the company is using Amazon SageMaker to build a model to recommend specific offers to each customer based on the customer's profile and the offers that the customer has accepted in the past.

Which solution will meet these requirements with the MOST operational efficiency?

Answer options

• A. Use the Factorization Machines algorithm to build a model that can generate personalized offer recommendations for customers. Deploy a SageMaker endpoint to generate offer recommendations. Feed the offer recommendations into the bulk email marketing system.
• B. Use the Neural Collaborative Filtering algorithm to build a model that can generate personalized offer recommendations for customers. Deploy a SageMaker endpoint to generate offer recommendations. Feed the offer recommendations into the bulk email marketing system.
• C. Use the Neural Collaborative Filtering algorithm to build a model that can generate personalized offer recommendations for customers. Deploy a SageMaker batch inference job to generate offer recommendations. Feed the offer recommendations into the bulk email marketing system.
• D. Use the Factorization Machines algorithm to build a model that can generate personalized offer recommendations for customers. Deploy a SageMaker batch inference job to generate offer recommendations. Feed the offer recommendations into the bulk email marketing system.

Correct answer: D

Explanation

Option D is correct because deploying a SageMaker batch inference job allows the company to efficiently process larger sets of data at once, which is ideal for generating recommendations for multiple customers simultaneously. In contrast, options A and B suggest using a SageMaker endpoint, which is less efficient for bulk processing, while option C, although efficient, uses the Neural Collaborative Filtering algorithm, which may not perform as well as Factorization Machines in this specific scenario.