MLA-C01 · Question #187
A company has built, trained, and tuned two new ML models: - Model A detects if a transaction is fraudulent based on the IP address, location, and user credentials. This model will be accessed every…
The correct answer is C. Host Model A with a real-time endpoint. Use batch transform for Model B. The fraud detection model must serve low-latency predictions for every transaction, which is best supported by a real-time endpoint. The sales forecasting model runs on a fixed monthly schedule and does not require low-latency responses, making batch transform the most…
Question
A company has built, trained, and tuned two new ML models:
- Model A detects if a transaction is fraudulent based on the IP
address, location, and user credentials. This model will be accessed every time a transaction occurs.
- Model B forecasts sales totals for the next month based on historical
sales data. This model will be accessed one time each month. The company must deploy both models to production by using Amazon SageMaker AI. Which hosting solution for the models should the company use to meet these requirements?
Options
- AHost both models in one container behind one real-time endpoint.
- BHost Model A with an asynchronous endpoint. Host Model B with a real-time endpoint.
- CHost Model A with a real-time endpoint. Use batch transform for Model B.
- DUse batch transform for Model A. Host Model B with an asynchronous endpoint.
How the community answered
(59 responses)- A8% (5)
- B5% (3)
- C83% (49)
- D3% (2)
Explanation
The fraud detection model must serve low-latency predictions for every transaction, which is best supported by a real-time endpoint. The sales forecasting model runs on a fixed monthly schedule and does not require low-latency responses, making batch transform the most cost-effective and appropriate hosting option.
Topics
Community Discussion
No community discussion yet for this question.