AWS Certified Machine Learning – Specialty — Question 339

A business to business (B2B) ecommerce company wants to develop a fair and equitable risk mitigation strategy to reject potentially fraudulent transactions. The company wants to reject fraudulent transactions despite the possibility of losing some profitable transactions or customers.

Which solution will meet these requirements with the LEAST operational effort?

Answer options

• A. Use Amazon SageMaker to approve transactions only for products the company has sold in the past.
• B. Use Amazon SageMaker to train a custom fraud detection model based on customer data.
• C. Use the Amazon Fraud Detector prediction API to approve or deny any activities that Fraud Detector identifies as fraudulent.
• D. Use the Amazon Fraud Detector prediction API to identify potentially fraudulent activities so the company can review the activities and reject fraudulent transactions.

Correct answer: C

Explanation

Using Amazon Fraud Detector, a fully managed service, requires significantly less operational effort than building and maintaining custom models in Amazon SageMaker. Automatically approving or denying transactions via the prediction API eliminates the need for manual review, aligning with the company's willingness to accept some lost transactions for the sake of efficiency. This makes option C the most efficient solution compared to option D, which requires manual intervention.