Also known as segmentation, separates data into groups where items in the same group are similar and items in different groups are dissimilar.

Also known as segmentation, separates data into groups where items in the same group are similar and items in different groups are dissimilar.

• A. Partitional Clustering
• B. PCA
• C. Data Clustering
• D. Orthogonality

Answer: (C)

Grouping data into clusters based on similarity captures the idea of segmentation: items that are alike end up in the same group, while dissimilar items fall into different groups. This is what data clustering does—an unsupervised process that discovers structure in data without predefined labels. Among the options, data clustering is the broad term that directly describes this segmentation behavior. Partitional clustering is a way to implement clustering (a method that partitions data into non-overlapping groups), but the description refers to the general concept of forming groups by similarity, which data clustering covers most directly. PCA, on the other hand, is about reducing dimensions, not creating groups, and orthogonality is a linear-algebra property about perpendicular directions, not about grouping data. So the best fit for the described idea is data clustering.

Grouping data into clusters based on similarity captures the idea of segmentation: items that are alike end up in the same group, while dissimilar items fall into different groups. This is what data clustering does—an unsupervised process that discovers structure in data without predefined labels. Among the options, data clustering is the broad term that directly describes this segmentation behavior. Partitional clustering is a way to implement clustering (a method that partitions data into non-overlapping groups), but the description refers to the general concept of forming groups by similarity, which data clustering covers most directly. PCA, on the other hand, is about reducing dimensions, not creating groups, and orthogonality is a linear-algebra property about perpendicular directions, not about grouping data. So the best fit for the described idea is data clustering.