Anda di halaman 1dari 2

BIDM Assignment No.

2 and 3
Segmentation Case
Submission Deadline
Assignment 2: Due on Tuesday, 22nd November
Assignment 3: Due on Tuesday, 29th November
Go through the Segmentation Case and the excel sheet uploaded on course website. Several
variables in this case deal measure aspects of brand loyalty. The number of different brands
purchased by the customer is one measure. However, a consumer who purchases one or two
brands in quick succession then settles on a third for a long streak is different from a
consumer who constantly switches back and forth among three brands. So, how often
customers switch from one brand to another is another measure of loyalty. Brand runs is the
no. of consecutive purchases of the same brand. Yet a third perspective on the same issue is
the proportion of purchases that go to different brands a consumer who spends 90% of his
or her purchase money on one brand is more loyal than a consumer who spends more
equally among several brands.
All three of these components can be measured with the data in the purchase summary worksheet.
Assignment no. 2
Your objective is to Use k-means clustering to identify clusters of households based on
a. The variables that describe purchase behavior (including brand loyalty).
b. The variables that describe basis-for-purchase.
c.

The variables that describe both purchase behavior and basis of purchase.

ASSIGNMENT NO. 2: Create at least 3 new derived variables that describe purchase
behavior and at least 2 new variables that describe basis for purchase. Explain what new
variables you have created and why? Which variables would be rejected (not used as input
to clustering) and why?
Note 1: How should k be chosen? Think about how the clusters would be used. It is likely that
the marketing efforts would support 2-4 different promotional approaches.
Note 2: How should the percentages of total purchases comprised by various brands be treated?
Isnt a customer who buys all brand A just as loyal as a customer who buys all brand B? What will
be the effect on any distance measure of using the brand share variables as is? Consider using a
single derived variable.
ASSIGNMENT NO. 3
Once you have created new variables, delete the first two rows of the excel sheet (the first row
has household, purchase summary etc and second row is blank). Open SAS and Follow the steps
to convert your transformed excel file into a SAS Dataset.
Use k-means clustering to identify clusters of households based on
d. The variables that describe purchase behavior (including brand loyalty).
e. The variables that describe basis-for-purchase.
f.

The variables that describe both purchase behavior and basis of purchase.

Note 1: How should k be chosen? Think about how the clusters would be used. It is likely that
the marketing efforts would support 2-4 different promotional approaches.
Open SAS Enterprise Miner, Create a new library and link the same to a folder in which SAS
Dataset is saved.

2. Develop various clustering schemes using k=2, 3 and 4 using the following variables.

The variables that describe purchase behavior (incl brand loyalty). Which variables
would be set to use in the cluster node and which variables would be set to use in
the segment profile node and why?

The variables that describe basis-for-purchase. Which variables would be set to


use in the cluster node and which variables would be set to use in the segment
profile node and why?

The variables that describe both purchase behavior and basis of purchase. Which
variables would be set to use in the cluster node and which variables would be set
to use in the segment profile node and why?

For each of the above; Select what you think is the best segmentation (explain how do you
select the best clustering/ segmentation scheme) and comment on the characteristics
(demographic, brand loyalty and basis-for-purchase) of these clusters. (This information
would be used to guide the development of advertising and promotional campaigns.)

Attach screenshots of clustering/ segment profile node results as


applicable.