Cluster Analsysis

Question 1

is finding groups of objects such that the objects in a group will be similar (or related) to one another and different from the object in other groups.

Answer 1

Cluster Analysis

Question 2

2 TYPES OF CLUSTERING

Answer 2

1. Partitional Clustering
2. Hierarchical Clustering

Question 3

4 Types of Clusters

Answer 3

1. Center-Based Clusters
2. Contiguity Clusters
3. Density-Based Clusters
4. Conceptual Clusters

Question 4

a type of cluster that is a set of objects such that an object in a cluster is closer to the “center” of a cluster, than to the center of any other cluster.

Answer 4

Center-Based Clusters

Question 5

the center of a cluster.

Answer 5

Centroid

Question 6

average of all points in the cluster.

Answer 6

Medoid

Question 7

a type of cluster where each point is closer to at least one point in its cluster than to any point in any other cluster.

Answer 7

Contiguity Clusters

Question 8

a type of cluster where
the cluster are regions of high density separated by regions of low density.

Answer 8

Density-Based Clusters

Question 9

a type of cluster where points in a cluster share some general property that derives from the entire set points.

Answer 9

Conceptual Clusters

Question 10

2 Objective Functions

Answer 10

1. Global Objective Function
2. Local Objective Function

Question 11

typically used in partitional clustering.

Answer 11

Global Objective Function

Question 12

3 Clustering Algorithms

Answer 12

1. K-Means Clustering
2. Hierarchical Clustering
3. Density-Based Clustering

Question 13

is a partitional clustering approach.

Answer 13

K-Means Clustering

Question 14

is the mean of the points in a cluster.

Answer 14

Centroid

Question 15

is used to measure “closeness”

Answer 15

Euclidean Distance

Question 16

will converge typically in the first few iterations.

Answer 16

K-Means

Question 17

3 Solution to Initial Centroid Problem: (randomly chosen centroids)

Answer 17

1. Multiple Runs
2. Sample and use hierarchical clustering to determine the initial centroids.
3. Select more than k initial centroid, and the select among those the one that are far away from each other.

Question 18

is the most common measure in evaluation K-means clusters.

Answer 18

Sum of Squared Error (SSE)

Question 19

2 Pre-Processing Methods for K-Means Clusters:

Answer 19

1. Normalize the data
2. Eliminate outliers.

Question 20

3 Post-Processing Methods for K-Means Clusters:

Answer 20

1. Eliminate small clusters that may represent outliers.
2. Split ‘loose’ clusters, clusters with high SSE
3. Merge clusters that are ‘close’ and that have relatively low SSE

Question 21

2 Limitations of K-Means Clusters:

Answer 21

o It has problem when clusters are of differing sizes, density, and non-globular shape.

o When data contains outliers.