A company wants to find groups for its customers based on the customers' demographics and buying patterns. Which algorithm should the company use to meet this requirement?

Question

Options

• AK-nearest neighbors (k-NN)
• BK-means
• CDecision tree
• DSupport vector machine

• A
  5% (3)
• B
  84% (47)
• C
  9% (5)
• D
  2% (1)

Explanation

K-means is the right choice because it is an unsupervised clustering algorithm designed specifically to group unlabeled data points (like customers) into distinct clusters based on their similarities - exactly what's needed when finding natural groupings in demographics and buying patterns without predefined labels.

Why the distractors are wrong:

• K-nearest neighbors (k-NN) is a supervised classification/regression algorithm that requires labeled training data to classify new data points - it doesn't discover groups on its own.
• Decision tree is a supervised learning algorithm used for classification or regression tasks where you already have labeled outcomes (e.g., "will buy" or "won't buy") - not for discovering unknown groupings.
• Support vector machine (SVM) is also a supervised algorithm used for classification and regression, requiring labeled data to find decision boundaries between known categories.

Memory tip: Think of the "K" in K-means as standing for "Kategorize" (group/cluster) - whenever a question asks about discovering or finding groups in data with no pre-existing labels, K-means is your go-to. A helpful phrase: "K-means clusters the unseen, while k-NN classifies the seen."

No community discussion yet for this question.