Practice Library
All MCQs
Browse exam-wise, subject-wise, and country-wise MCQs with explanations.
Choose an option to check your answer.
A.
Anomalies are isolated with fewer random partitioning steps
B.
Anomalies have the largest class priors
C.
Anomalies form the deepest clusters
D.
Anomalies maximize association support
Show Answer
Correct Answer: A. Anomalies are isolated with fewer random partitioning steps
Explanation:
Rare, extreme points tend to separate early in random trees.
Choose an option to check your answer.
A.
Distances cannot be computed
B.
Dense regions contain no anomalies
C.
All points have equal distance
D.
Normal points in sparse regions may look anomalous
Show Answer
Correct Answer: D. Normal points in sparse regions may look anomalous
Explanation:
One global cutoff assumes comparable density everywhere.
Choose an option to check your answer.
A.
Its class probability with the global mean
B.
Its support with confidence
C.
A point's local density with the densities of its neighbors
D.
Its tree depth with sample size
Show Answer
Correct Answer: C. A point's local density with the densities of its neighbors
Explanation:
A point is suspicious when it lies in a much sparser neighborhood than nearby points.
Choose an option to check your answer.
A.
It flags points with common labels
B.
It flags points far from their neighbors
C.
It uses rule confidence only
D.
It finds the deepest tree leaves
Show Answer
Correct Answer: B. It flags points far from their neighbors
Explanation:
Anomalies often occupy isolated regions of feature space.
Choose an option to check your answer.
A.
Mostly or exclusively normal examples
B.
Only labeled anomalies
C.
No data at all
D.
Frequent itemsets only
Show Answer
Correct Answer: A. Mostly or exclusively normal examples
Explanation:
The model learns the normal region and flags departures.
Choose an option to check your answer.
A.
Predicting known anomaly classes
B.
Using a balanced labeled set
C.
Removing all low-frequency values
D.
Identifying rare or structurally unusual observations without anomaly labels
Show Answer
Correct Answer: D. Identifying rare or structurally unusual observations without anomaly labels
Explanation:
Unsupervised methods assume anomalies differ from dominant data structure.
Choose an option to check your answer.
A.
Clustering entirely unlabeled data
B.
Using only frequent items
C.
Learning from examples labeled normal and anomalous
D.
Detecting anomalies without features
Show Answer
Correct Answer: C. Learning from examples labeled normal and anomalous
Explanation:
The task becomes an imbalanced classification problem when labels are available.
Choose an option to check your answer.
A.
A single extreme numeric value
B.
A group of observations whose combined pattern is abnormal
C.
The largest cluster
D.
A missing transaction
Show Answer
Correct Answer: B. A group of observations whose combined pattern is abnormal
Explanation:
Individual members may appear normal in isolation.
Choose an option to check your answer.
A.
An observation abnormal only under a particular context
B.
An observation abnormal in every dataset
C.
A duplicated normal record
D.
A class centroid
Show Answer
Correct Answer: A. An observation abnormal only under a particular context
Explanation:
Context may include time, location, season, or user group.
Choose an option to check your answer.
A.
A normal observation in a rare class
B.
A missing attribute name
C.
A frequent itemset
D.
A single observation that is unusual relative to the rest of the data
Show Answer
Correct Answer: D. A single observation that is unusual relative to the rest of the data
Explanation:
Point anomalies are individually abnormal without needing additional context.
Choose an option to check your answer.
A.
SOM cannot use numeric features
B.
Every unit must contain one class
C.
The low-dimensional layout can distort some high-dimensional relationships
D.
SOM always returns a linear boundary
Show Answer
Correct Answer: C. The low-dimensional layout can distort some high-dimensional relationships
Explanation:
No low-dimensional projection preserves every distance and neighborhood perfectly.
Choose an option to check your answer.
A.
The number of mislabeled classes
B.
The average distance from inputs to their best matching units
C.
The support lost during pruning
D.
The variance of grid coordinates only
Show Answer
Correct Answer: B. The average distance from inputs to their best matching units
Explanation:
Quantization error measures how well prototypes represent the observations.
