Unsupervised Learning: Clustering for Competitive Exams

Unsupervised Learning: Clustering - Numerical Applications

Q. In DBSCAN, what does the term 'epsilon' refer to?

Solution

'Epsilon' defines the maximum distance between two points for them to be considered part of the same cluster in DBSCAN.

Correct Answer: B — The maximum distance between two points to be considered in the same cluster

Q. What is the main advantage of using DBSCAN over K-Means?

Solution

DBSCAN can find clusters of arbitrary shape, making it more flexible than K-Means.

Correct Answer: B — It can find clusters of arbitrary shape

Q. What type of data is best suited for clustering algorithms?

Solution

Clustering algorithms are designed to work with unlabeled data to find inherent groupings.

Correct Answer: B — Unlabeled data

Q. Which clustering algorithm is best for identifying spherical clusters?

Solution

K-Means is effective for identifying spherical clusters due to its centroid-based approach.

Correct Answer: C — K-Means

Q. Which evaluation metric is NOT typically used for clustering algorithms?

Solution

Accuracy is not applicable to clustering since it is an unsupervised learning method without labeled data.

Correct Answer: C — Accuracy

Q. Which of the following algorithms is commonly used for clustering numerical data?

Solution

K-Means is a popular algorithm for clustering numerical data by partitioning it into K distinct clusters.

Correct Answer: B — K-Means

Q. Which of the following is an application of clustering in real-world scenarios?

Solution

Customer segmentation in marketing uses clustering to group customers based on purchasing behavior.

Correct Answer: B — Customer segmentation in marketing

Showing 1 to 7 of 7 (1 Pages)