Scribd
Upload
336 views

Data Mining Assignment

This document discusses applying clustering analysis techniques to customer data from an airline's frequent flyer program to identify customer segments. 1) Hierarchical clustering with Ward's method and Euclidean distance on standardized data identified 3 clusters of customers. 2) The cluster centroids were compared to characterize the different clusters and label them. 3) Repeating the analysis on a 95% random sample showed the same 3 clusters, indicating the clusters are stable. 4) K-means clustering with 3 clusters produced similar results, validating the hierarchical clustering results.

Uploaded by

anjali9414
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
336 views

Data Mining Assignment

This document discusses applying clustering analysis techniques to customer data from an airline's frequent flyer program to identify customer segments. 1) Hierarchical clustering with Ward's method and Euclidean distance on standardized data identified 3 clusters of customers. 2) The cluster centroids were compared to characterize the different clusters and label them. 3) Repeating the analysis on a 95% random sample showed the same 3 clusters, indicating the clusters are stable. 4) K-means clustering with 3 clusters produced similar results, validating the hierarchical clustering results.

Uploaded by

anjali9414
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

7/6/2017 RPubs - Dummy

RPubs
Dummy
brought to you by RStudio
by subba reddy Yeruva Last updated 12 months ago Comments () Share
Sign in Register
Hide Toolbars

Batch 6 - Data Mining 1 - Unsupervised


Learning - Assignment 1
Subba Reddy Yeruva, ISB Id: 71610085
06 July 2016

1. Marketing to Frequent Fliers


The file EastWestAirlinesCluster.xls (available on the textbook website http://dataminingbook.com/
(http://dataminingbook.com/)) contains information on 4000 passengers who belong to an airlines frequent flier
program. For each passenger the data include information on their mileage history and on different ways they
accrued or spent miles in the last year. The goal is to try to identify clusters of passengers that have similar
characteristics for the purpose of targeting different segments for different types of mileage offers.

1.1 Apply hierarchical clustering with Euclidean distance and Wards method. Make sure to standardize the
data first. How many clusters appear?

1.2 What would happen if the data were not standardized?

1.3 Compare the cluster centroids to characterize the different clusters and try to give each cluster a label.

1.4 To check the stability of the clusters, remove a random 5% of the data (by taking a random sample of 95%
of the records), and repeat the analysis. Does the same picture emerge?

1.5 Use k-means clustering with the number of clusters that you found above in Part (a). Does the same
picture emerge? If not, how does it contrast or validate the finding in Part c above?

1.6 Which cluster(s) would you target for offers, and what type of offers would you target to customers in that
cluster? Include proper reasoning in support of your choice of cluster(s) and the corresponding offer(s).

1.1 Number of Clusters


As per the nature of the columns in EastWestAirlinesCluster.xls, The data is mixed data. Hence the categorical
variables are converted into binary and then clustering is applied.

As per the generated dendogram below, if slicing is done at height 100 then there are 3 clusters formed.

As per the dendogram branching is done into 2 parts and left branch alone formed one cluster and 2nd
branch(Right Branch) again splitted into two more branches. The two branches of right branch are formed into
an cluster. Hence in total 3 clusters with maximum number of customers.

R code illustrating the procees to create


Hierarchical Clustering

https://rpubs.com/yeruva_s_reddy/194667 1/1

You might also like