survey on consumer purchase
TRANSCRIPT
A PROJECT REPORT
ONCONSUMER PURCHASE DECISION
KIRANA STORES VS SUPER MARKETS
SUBMITTED TO: - PROF. SUSHAMA MARATHE
BY :-
AMRITA KASHYAP 09BSHYD0082 (SEAT NO 5) SECTION –K
ANUROOP SINGH 09BSHYD0149 (SEAT NO 3) DATE: - 15/1/2010
GAURAV MADAN 09BSHYD0288 (SEAT NO 7) GROUP NO. 1
KHUSHBU BANSAL 09BSHYD0368 (SEAT NO 9)
PREETISH KR. SINGH 09BSHYD0585 (SEAT NO 1)
HAKAIM SUMAIR RIYAZ 09BSHYD0305 (SEAT NO 11)
ACKNOWLEDGEMENT
We wish to express our sincere gratitude to PROF.SUSHAMA MARATHE, Dept. of Operations
and Systems, IBS Hyderabad for providing us an opportunity to do this project work titled
“CONSUMER PURCHASE DECISION: KIRANA STORES VS SUPERMARKETS” .We
sincerely thank our project mentor for her guidance and encouragement in carrying out this project
work .
AMRITA KASHYAP
ANUROOP SINGH
GAURAV MADAN
KHUSHBU SINHA
PREETISH KR. SINGH
HAKAIM SUMAIR RIYAZ
Place: Hyderabad
Date: 15.01.10
TABLE OF CONTENTS
1. Acknowledgement
2. Executive summary
3. Introduction
4. Methodology
a. Research Design.
b. Sampling Design.
c. Data collection.
d. Sample questionnaire.
e. Coding of data.
5. Data analysis and Discussion
6. Conclusion.
7. References.
Executive Summary
The purpose of our study was to study and analyze the differentiating factors that affects the
consumer’s purchase decisions between local Kirana stores and Supermarkets. A Questionnaire was
designed to record the response of consumers with respect to 13 important factors that determine the
purchasing decisions of consumers.
Data was collected from different Supermarkets and Kirana stores of Hyderabad. The sample size was 150.
The data was coded and analyzed in SPSS ver. 13.0. To analyze we performed cluster analysis. The rationale
of using the cluster analysis was to group together those factors which influenced a person to purchase from
a Kirana store or a Supermarket. Upon observation of the result three clusters(each cluster grouped together
certain factors which explained the purchasing decisions of that particular cluster) came up. Cluster 3
reflected the purchasing behavior that of a person buying from Local Kirana store. Cluster 2 explained the
purchasing behavior of a person buying from Supermarket. And Cluster 1 represented people who didn’t
seem to follow a particular purchasing behavior as no factor significantly triggered their purchasing
decisions.
Introduction
Food and grocery(F&G) segment comprises 62% of the 270 billion Indian retail market. Only 0.8%
of this segment is in organized sector and the organized F&G sector witnessed a year-on-year
growth of 30% as against 2.2% growth of the total F&G retail market in recent years.
This indicates huge opportunity in organized retail sector. Although traditional retail currently
constitutes over 95% of the total sales in the country, smaller Kiranas(Indian version of a
combination of convenience and mom-and-pop stores with <500sq ft area) that are unable to
compete with new age retailers in terms of variety and scale have begun losing volume and share of
customer’s wallet in several parts of the country.
Methodology.
Objective: To study the differentiating factors involved that affects the consumer’s purchase decisions
between local kirana stores and Supermarkets.
Research question: What makes consumers buy from Kirana stores or Supermarkets?
Research Design
A research design is a framework or blueprint for conducting the marketing research project. It details the
procedures necessary for obtaining the information needed to structure or solve marketing research problems
Research design process comprises of
Planning
Selecting method
Define the information needed.
Design the exploratory, descriptive, and/or causal phases of the research
Specify the measurement and scaling procedures
Construct and pretest a questionnaire for data collection
Specify the sampling process and sample size
Conducting survey
o Survey will be used to collect quantitative information about factors from the population.
The survey will focus on collecting factual information as per the purpose.
Develop a plan of data analysis
Sampling Design
Sampling is process or technique of selecting a part of population for purpose of determining the
characteristics of whole population.
Some basic things
Population: - The entire aggregation of items from which samples can be drawn. N indicates the size of
Population
Sample: -Sample is part of total population. It is subset of population and it represents population. n
indicates the size of Sample
Data collection
Data was collected from customers visiting different Supermarkets(Food Bazaar and
More) and Kirana stores in Hyderabad. The size of the sample was 150.
Research Questionnaire
A research questionnaire was prepared to record the response of the sample size. Please refer to the
Annexure 1 to see the questionnaire.
CODING OF THE DATA
GENDER:
MALE 1
FEMALE 2
FAMILY INCOME:
LESS THAN 1 LAC 1
1 LAC TO LESS THAN 2 LAC 2
2 LACS TO LESS THAN 3 LACS 3
3 LACS TO LESS THAN 4 LACS 4
4 LACS AND ABOVE 5
DAILY NEEDS PURCHASED FROM:
SUPER MARKET 1
KIRANA STORE 2
PURCHASING PATTERN:
BULK BUYING 1
AS PER REQUIREMENTS 2
REGULAR VISITOR:
YES 1
NO 2
DURATION OF BEING A CUSTOMER:
LESS THAN 1 YEAR 1
1 YEAR TO LESS THAN 2 YEARS 2
2 YEARS TO LESS THAN 3 YEARS 3
3 YEARS AND ABOVE 4
SATISFACTION WITH THE REGULAR STORE:
VERY SATISFIED 5
SATISFIED 4
NEUTRAL 3
DISSATISFIED 2
EXTREMELY DISSATISFIED1
ON A SCALE OF 5 THE FOLLOWING FACTORS ARE WEIGHTED WHICH INFLUENCE THE
CHOICE OF PURCHASING OUTLET-
STRONGLY AGREE 5
AGREE 4
NEUTRAL 3
DISAGREE 2
STRONGLY DISAGREE 1
1.LOCATION
2.DISCOUNTS
3.TRUST
4.AVAILABILITY
5.AMBIENCE
6.HOME DELIVERY
7.INFLUENCE OF FRIENDS
8.LOYALTY
9.PROMOTIONAL SCHEMES
10.CREDIT AVAILABILITY
11.QUICK SERVICE
12.STAFF ASSISTANCE
13.CREDIT/DEBIT CARD PAYMENT
Analysis and DiscussionCluster analysis, also called segmentation analysis or taxonomy analysis, seeks to identify
homogeneous subgroups of cases in a population. That is, cluster analysis is used when the
researcher does not know the number of groups in advance but wishes to establish groups and then
analyze group membership. Cluster analysis implements this by seeking to identify a set of groups
which both minimize within-group variation and maximize between-group variation.
Key Concepts and Terms
o Cluster formation is the selection of the procedure for determining how clusters are created, and
how the calculations are done. In agglomerative hierarchical clustering every case is initially
considered a cluster, then the two cases with the lowest distance (or highest similarity) are
combined into a cluster. The case with the lowest distance to either of the first two is considered
next. If that third case is closer to a fourth case than it is to either of the first two, the third and
fourth cases become the second two-case cluster; if not, the third case is added to the first cluster.
The process is repeated, adding cases to existing clusters, creating new clusters, or combining
clusters to get to the desired final number of clusters.
o Cluster validity . The utility of clusters must be assessed by three criteria:
1. Size. All clusters should have enough cases to be meaningful. One or more very small clusters
indicates the researcher has requested too many clusters. Analysis resulting in a very large,
dominant cluster may indicate too few clusters have been requested.
2. Meaningfulness. As in factor analysis, ideally the meaning of each cluster should be readily
intuited from the constituent variables used to create the clusters. Variable importance plots,
discussed below, are one method of making this assessment.
3. Criterion validity. The crosstabulation of the cluster id numbers by other variables known from
theory or prior research to correlate with the concept which clustering is supposed to reflect, should
in fact reveal the expected level of association.
Failure to meet these criteria may indicate the researcher has requested too many or too few
clusters, or possibly that an inappropriate distance measure (discussed below) has been selected. It
is also possible that the hypothesized conceptual basis for clustering does not exist, resulting in
arbitrary clusters.
o Distance (proximities ). The first step in cluster analysis is establishment of the similarity or
distance matrix. This matrix is a table in which both the rows and columns are the units of analysis
and the cell entries are a measure of similarity or distance for any pair of cases.
Hierarchical Cluster Analysis
o Hierarchical clustering is appropriate for smaller samples (typically < 250). When n is large, the
algorithm will be very slow to reach a solution. To accomplish hierarchical clustering, the
researcher must specify how similarity or distance is defined and how clusters are aggregated (or
divided). Hierarchical clustering generates all possible clusters of sizes 1...K, but is used only for
relatively small samples. In hierarchical clustering, the clusters are nested rather than being
mutually exclusive, as is the usual case. That is, in hierarchical clustering, larger clusters created at
later stages may contain smaller clusters created at earlier stages of agglomeration.
The basic criterion for any clustering is distance. Objects that are near each other should belong to
the same cluster, and objects that are far from each other should belong to different clusters. For a
given set of data, the clusters that are constructed depend on your specification of the following
parameters:
Cluster method defines the rules for cluster formation. For example, when calculating the
distance between two clusters, you can use the pair of nearest objects between clusters or the pair of
furthest objects, or a compromise between these methods.
Measure defines the formula for calculating distance. For example, the Euclidean distance
measure calculates the distance as a "straight line" between two clusters. Interval measures assume
that the variables are scale; count measures assume that they are discrete numeric; and binary
measures assume that they take only two values.
Standardization allows you to equalize the effect of variables measured on different scales.
Case Processing Summary(a,b)
Cases
Valid Missing Total
N Percent N Percent N Percent
150 100.0 0 .0 150 100.0
a Squared Euclidean Distance used
b Average Linkage (Between Groups)
Squared Euclidean distance removes the sign and also places greater emphasis on objects further
apart, thus increasing the effect of outliers. This is the default for interval data.
Between-groups linkage, also called UPGMA linkage (unweighted pair-group method using
averages), is the default. The distance between two clusters is the average distance between all
inter-cluster pairs. This method is generally preferred over nearest or furthest neighbor methods
since it is based on information about all inter-cluster pairs, not just the nearest or furthest ones.
This method works well for both elongated chain-type and with clumpy type clusters.
Agglomeration Schedule. Agglomeration schedule is a choice under the Statistics button for
Hierarchical Cluster in the SPSS Cluster dialog. In this table, the rows are stages of clustering,
numbered from 1 to (n - 1). The (n - 1)th stage includes all the cases in one cluster. There are two
"Cluster Combined" columns, giving the case or cluster numbers for combination at each stage. In
agglomerative clustering using a distance measure like Euclidean distance, stage 1 combines the
two cases which have lowest proximity (distance) score. The cluster number goes by the lower of
the cases or clusters combined, where cases are initially numbered 1 to n.
The proximity/distance/agglomeration coefficient in the "Coefficients" column is an indicator of
how far the agglomeration algorithm has to reach to combine an existing cluster with the next
closest cluster or variable (judge). For this example one can see that there is a large jump between
stages 5 and 6, corresponding to combining cluster 1 (judges 2,5,7, and 1) with cluster 2 (judges 2,
4, and 6) from stage 5. A large agglomeration coefficient will correspond with a long distance in the
dendogram discussed below. When there are relatively few cases, icicle plots or dendograms
provide the same linkage information in an easier format.
K-means Cluster Analysis
o K-means cluster analysis . Large datasets are possible with K-means clustering, unlike
hierarchical clustering, because K-means clustering does not require prior computation of a
proximity matrix of the distance/similarity of every case with every other case. Because cases may
be shifted from one cluster to another during the iterative process of converging on a solution, k-
means clustering is a type of "relocation clustering method
o K-means cluster analysis uses Euclidean distance. We must specify in advance the desired
number of clusters, K. Initial cluster centers are chosen randomly in a first pass of the data, then
each additional iteration groups observations based on nearest Euclidean distance to the mean of the
cluster. Cluster centers change at each pass. The process continues until cluster means do not shift
more than a given cut-off value or the iteration limit is reached.
Iteration History
This table shows the progress of the estimation process at each iteration. At each iteration, as cases
are reassigned to different cluster, cluster centers change. Each number indicates how far the new
cluster center is from the cluster center at the previous iteration. When the change is small enough
for all clusters, iteration stops and the final solution is reached.
Iteration History(a)
Iteration
Change in Cluster Centers
1 2 3
1 4.089 4.926 4.878
2 .591 .679 1.399
3 .624 .471 .565
4 .461 .291 .176
5 .256 .126 .116
6 .116 .073 .000
7 .000 .000 .000
a Convergence achieved due to no or small change in cluster centers. The maximum absolute coordinate change for any center
is .000. The current iteration is 7. The minimum distance between initial centers is 9.055.
Here each no. indicates how far the new cluster center is from the cluster center at the previous iteration e.g 0.591 indicates that new
cluster center is 0.591 units away from the cluster center of previous iteration.
Final Cluster Centers.
This table shows the values for the final cluster centers. The values in the table are the means for each variable within each
final cluster. The final clusters centers reflect the attributes of the prototypical case for each cluster
Cluster
1 2 3
Location 1.54 4.39 4.71
Discounts 3.39 3.92 1.44
Trust with the shopkeeper 1.63 3.80 4.73
availability of products 2.17 4.28 3.16
Ambiance 3.15 3.75 1.60
Home delivery 2.63 3.41 3.13
Influence of friends/ family 3.29 3.19 2.87
loyalty to the outlet 2.93 3.58 3.27
Promotional schemes 3.17 3.89 2.96
credit availability 2.61 3.52 4.53
Quick Service 2.93 3.16 4.16
staff assistance 3.90 4.22 1.71
Credit/debit card payment 3.54 4.03 1.31
According to our analysis the different points were observed with respect to different clusters. Viz.
Cluster 3. In this cluster following factors primarily play an important role in determining the
purchasing behavior: Location, Trust with shopkeeper, Credit availability and Quick service.
This group of people are those who are conventional buyers. These kind of people base their
purchasing decisions on the ease of procuring. Ease of procurement here defines both the nearness
of distance of the store and quickness of purchasing . Relationship with the retailer also plays an
important in their case. The usually rely on the advice of the retailer. Whether or not the retailer
allows credit purchases also is an important factor here.
Cluster 2. In this cluster following factors primarily play an important role in determining the
purchasing behavior: Discounts, Availability of Product, promotional schemes, Ambience, Staff
assistance and Credit/Debit card payment.
This group represents a set of people who are active shoppers. Active shoppers here mean those
people who gather a lot of information about the products and their prices they want to buy. This
behavior is likely to be that of an educated buyer who takes informed decisions. They also take into
account the place from where they buy. Also these people want convenience in the way they pay.
Cluster 1. In this cluster, there is not any clarity about the factors that play a role in determining
the purchasing behavior, however the factor that scores highest here is Influence of
Family/Friends.
Also the factors that can be secondarily associated here are: discount, promotional schemes, staff
assistance and credit/debit card payments
This group doesn’t seem to follow a particular purchasing behavior as no factor significantly
triggers their purchasing decisions. Influence of peers scores highest, thus we can say these buyers
keep changing their purchasing pattern.
Conclusion.
We performed cluster analysis of the data provided. The result gave 3 distinct clusters explaining
the purchasing behaviors of various people. On the basis of the results we are able to conclude the
following:
The people that buy from Kirana store look for convenience of buying in terms of distance of the
stores from their homes and the quickness of purchasing. They also rely on the relationship factor.
The people that purchase from Supermarket look for different discounts and promotional schemes.
They also take into account the ambience and the staff assistance at the store. These people also
want convenience in the way they pay.
References
1. http://www.ibef.org/industry/retail.aspx
2. http://www.indianground.com/articles/Miscellaneous-articles/organised-retail-in-
india.aspx
3. http://www.statsoft.com/textbook/cluster-analysis/ important
4.
5. http://faculty.chass.ncsu.edu/garson/PA765/cluster.htm
6. http://en.wikipedia.org/wiki/Category:Supermarkets_of_India
7. Goswami Paromita, Mishra Mridula S., “Would Indian Consumersmove from Kirana
stores to organized retailers when shopping for groceries”, Emerald Insight Publications.
8. Zikmund William G., “Business Research Methods”, 7th Edition, South-Western College
Publications.