AWS Certified Machine Learning – Specialty — Question 165

A company has an ecommerce website with a product recommendation engine built in TensorFlow. The recommendation engine endpoint is hosted by Amazon
SageMaker. Three compute-optimized instances support the expected peak load of the website.
Response times on the product recommendation page are increasing at the beginning of each month. Some users are encountering errors. The website receives the majority of its traffic between 8 AM and 6 PM on weekdays in a single time zone.
Which of the following options are the MOST effective in solving the issue while keeping costs to a minimum? (Choose two.)

Answer options

• A. Configure the endpoint to use Amazon Elastic Inference (EI) accelerators.
• B. Create a new endpoint configuration with two production variants.
• C. Configure the endpoint to automatically scale with the InvocationsPerInstance metric.
• D. Deploy a second instance pool to support a blue/green deployment of models.
• E. Reconfigure the endpoint to use burstable instances.

Correct answer: A, C

Explanation

Choosing options A and C provides cost-effective solutions to enhance performance. Option A introduces Amazon Elastic Inference, which accelerates TensorFlow model inference without significant cost increases. Option C allows for dynamic scaling based on traffic, ensuring resources are utilized efficiently during peak times. The other options either do not directly address the performance issues or may incur higher costs without guaranteeing improved response times.