CLF-C02 Practice Question 89: Custom ML Models
AWS Certified Cloud Practitioner (CLF-C02) · Test 9 · question 9 of 10
A manufacturer's data science team wants to build its own machine learning model that predicts equipment failures from years of proprietary sensor data. The team needs managed infrastructure to prepare data, train and tune the model, and then deploy it to a production-ready hosted endpoint, without building and managing its own servers. Which AWS service should the team use?
Show answer and explanation
Answer:
Amazon SageMaker AI (called Amazon SageMaker until it was renamed in December 2024) is a fully managed machine learning service. It lets data scientists and developers build, train and deploy ML models into a production-ready hosted environment, with managed algorithms and support for their own algorithms and frameworks. Training a custom predictive model on the company's own sensor data is exactly this workflow.
Option A, Amazon Comprehend, is a pre-trained natural language processing service for extracting insights such as sentiment and entities from *text*. It does not train models on sensor readings. Option B, Amazon Rekognition, analyzes *images and videos*. Option C, Amazon Bedrock, provides access to foundation models for building *generative AI* applications. It is not the tool for training a custom predictive model from tabular sensor data.
Reference: What is Amazon SageMaker AI?