Data Science Data Science Unsupervised Learning Techniques Questions and Answers 2 — Questions and Answers
Question 1: Which unsupervised learning technique reduces the dimensionality of data by finding principal components that maximize variance?
- Principal Component Analysis (PCA) (Correct answer)
- K-Means Clustering
- DBSCAN
- Apriori Algorithm
Correct answer: Principal Component Analysis (PCA)
PCA identifies orthogonal axes (principal components) that capture the maximum variance in the dataset, effectively reducing dimensionality.
Question 2: In DBSCAN clustering, what is a 'core point'?
- A point with at least minPts neighbors within epsilon distance (Correct answer)
- The centroid of a cluster
- A point that lies on the boundary of two clusters
- The first point selected during initialization
Correct answer: A point with at least minPts neighbors within epsilon distance
A core point in DBSCAN is defined as a point that has at least minPts data points within its epsilon-radius neighborhood.
Question 3: What does the silhouette coefficient measure in cluster analysis?
- How similar a point is to its own cluster compared to neighboring clusters (Correct answer)
- The total number of clusters in the dataset
- The variance explained by each cluster
- The distance between cluster centroids
Correct answer: How similar a point is to its own cluster compared to neighboring clusters
The silhouette coefficient ranges from -1 to 1 and measures how well each data point fits within its assigned cluster versus the nearest neighboring cluster.
Question 4: Which unsupervised technique is most appropriate for detecting unusual transactions in credit card data without labeled fraud examples?
- Anomaly detection using Isolation Forest (Correct answer)
- Linear regression
- Naive Bayes classification
- Decision tree classification
Correct answer: Anomaly detection using Isolation Forest
Isolation Forest is an unsupervised anomaly detection method that isolates outliers by randomly partitioning data, making it ideal for fraud detection without labels.
Question 5: What is the primary purpose of t-SNE in unsupervised learning?
- Visualizing high-dimensional data in 2D or 3D space (Correct answer)
- Predicting continuous target variables
- Performing feature selection
- Building decision boundaries
Correct answer: Visualizing high-dimensional data in 2D or 3D space
t-SNE (t-distributed Stochastic Neighbor Embedding) is a nonlinear dimensionality reduction technique primarily used for visualizing complex high-dimensional datasets.
Question 6: In hierarchical agglomerative clustering, what does 'complete linkage' use to measure distance between two clusters?
- The maximum distance between any pair of points from the two clusters (Correct answer)
- The minimum distance between any pair of points from the two clusters
- The average distance between all pairs of points
- The distance between cluster centroids
Correct answer: The maximum distance between any pair of points from the two clusters
Complete linkage defines inter-cluster distance as the maximum distance between any single pair of points from each cluster, tending to produce compact clusters.
Data Science Data Science Unsupervised Learning Techniques Questions and Answers 2
Which unsupervised learning technique reduces the dimensionality of data by finding principal components that maximize variance?