Science and Education Publishing
From Scientific Research to Knowledge
Submission
Browse by Subjects
Search
Journal Home
For Authors
Online Submission
Current Issue
Archive
About Us
Figures index
From
Incorporating K-means, Hierarchical Clustering and PCA in Customer Segmentation
Azad Abdulhafedh
Journal of City and Development
.
2021
, 3(1), 12-30
Figure 1
.
frequency histograms of some main variables in the dataset
Full size figure and legend
Figure 2
.
the correlation matrix of the variables in the dataset
Full size figure and legend
Figure 3
.
dendrogram of the single linkage method
Full size figure and legend
Figure 4
.
dendrogram of the complete linkage method
Full size figure and legend
Figure 5
.
dendrogram of the average linkage method
Full size figure and legend
Figure 6
.
cutting the dendrogram
Full size figure and legend
Figure 7
.
Clusters resulted from fitting the Hierarchical clustering into the dataset
Full size figure and legend
Figure 8
.
finding optimal number of clusters using the elbow method
Full size figure and legend
Figure 9
.
Silhouette method for optimal number of clusters
Full size figure and legend
Figure 10
.
Gap statistic method for optimal number of clusters
Full size figure and legend
Figure 11
.
Clusters resulted by fitting K-means into the credit card dataset
Full size figure and legend
Figure 12
.
correlation matrix of the variables after applying the PCA
Full size figure and legend
Figure 13
.
the scree plot for finding the optimal number of PCs
Full size figure and legend
Figure 14
.
the cumulative percent of variance explained by the PCs
Full size figure and legend
Figure 15
.
PC2 against PC2
Full size figure and legend
Figure 16
.
PC2 against PC3
Full size figure and legend
Figure 17
.
PC3 against PC4
Full size figure and legend
Figure 18
.
PC4 against PC5
Full size figure and legend
Figure 19
.
contributions of variables to the 5 optimal PCs
Full size figure and legend
Figure 20
.
clusters resulted from applying the PCA
Full size figure and legend
Figure 21
.
clusters resulted from applying the PCA to the dataset
Full size figure and legend
Figure 22
.
AVERAGE Silhouette width score for the updated K-means clustering
Full size figure and legend
Figure 23
.
histograms of the four clusters or groups
Full size figure and legend