Question

We have a dataset with 10 different features for 500 college students. We want to know if we can group the students based on some similarities in their features. What method can be used for this problem.

Group of answer choices

A. K Fold

B. Classification Tree

C. K-Means

D. Logistic Regression

Answer 1

Please don't hesitate to give a "thumbs up" for the answer in case the answer has helped you

We have 10 features, with 500 observations.

We want to check if we can see group students by similarties of their features. We don't know the groupings yet - so Classification Tree and Logistic Regression is ruled out. Also, K-Fold technique is for cross validation it is not a technique used to what we want to acheive in the question.

So, we must use the unsupervised learning technique of K-Means Clustering which takes into account all the features, and groups observations into different "clusters" - groups with same properties/ very similar features.

Answer: C. K-Means is correct