AWS Certified Big Data – Specialty — Question 51

A company is using Amazon Machine Learning as part of a medical software application. The application will predict the most likely blood type for a patient based on a variety of other clinical tests that are available when blood type knowledge is unavailable.
What is the appropriate model choice and target attribute combination for this problem?

Answer options

• A. Multi-class classification model with a categorical target attribute.
• B. Regression model with a numeric target attribute.
• C. Binary Classification with a categorical target attribute.
• D. K-Nearest Neighbors model with a multi-class target attribute.

Correct answer: A

Explanation

The correct answer is A because the problem involves predicting one of several possible blood types, which fits a multi-class classification model that uses a categorical target attribute. Options B and C are incorrect as they do not align with the need for multiple categories, and option D is also incorrect because K-Nearest Neighbors does not specifically address the requirement for a categorical target attribute in this context.