Market Segmentation
Analysing the respective market in India using Segmentation analysis for Online Food
Delivery Startup
by
Group 2
Nikhitha Pasula
Apil Thapa
Gaurav Koli
Overview
Analysing the respective market in India using Segmentation analysis for Online Food
Delivery Startup delivering dairy items as their first product delivery
Segmentation analysis is an important step before we embark on a marketing plan. It is
important to learn how to analyze your audience and market.
Global Dairy Products Market is segmented By Product Type (Milk, Skimmed Milk Powder,
Whey Milk Powder, Whey Protein, Butter, Cheese, Yogurt, Others), By Distribution Channel
(Supermarkets & Hypermarkets, Convenience Stores, Online, others), and By Region (North
India ,East India ,West India ,South India) – Share, Size, Outlook, and Opportunity Analysis,
2020-2027.
India, in particular, is expected to witness the fastest growth rate in the regional market due
to the increasing demand for value-added dairy products like yogurt and cheese.
The E-commerce or online market in India is thriving very rapidly, making it one of the
fastest growing online markets in the world. Online food delivery market in India is one of its
segments, which is growing at a double-digit CAGR. During early days, online food ordering
and the delivery market was mainly concentrated on pizza, burger and such while now this
idea has immersed to the bulk of the food industry. With the growing penetration of the
internet, a new wave of online services including ordering and delivery of food has come to
the forefront of this marketplace. These food aggregators allow customers to compare
menus, prices, reviews and then place their orders from a wide network of restaurants
conveniently.
India Online Food Delivery Market is showing immense potential and attracting huge
investments. The online food delivery market of India is mainly driven by India's young
population base, increasing digitization, growing penetration of smartphones, increasing
disposable income of people in the region, a rising proportion of women in the working
population and adoption of aggressive marketing strategies by food start-ups.
Features, like ordering food and getting it delivered at the comfort of anytime anywhere with
the convenience of either online payment or pay on delivery, are some of the other factors
which are anticipated to further drive the growth of India Online Food Delivery Market. In
addition, lucrative offers, easy & user-friendly interface, cash-backs, social media, and
customer integration are also helping the online food delivery market to grow in the forecast
period.
Bangalore is the Leading City in the India Online Food Delivery Market.
Market Overview
The Global Dairy Products Market is expected to grow at a high CAGR during the forecast
period (2020-2027)
Dairy is one of the early food categories adopted by mankind and is considered as a major
part of human nutrition. Dairy products are primarily produced from milk and commercial
dairy include products ranging from liquid milk to processed products such as yogurt,
cheese, butter, and others. The health benefits associated with milk have been motivating
the population of all segments towards consumption of dairy based products. Dairy is
considered as a package of nutrients essential for a human body and is highly
recommended as a source of calcium and healthy fats.
Fig: Dairy Products Market-Overview
The global dairy products market size was valued at USD 481.08 billion in 2019 and is
expected to grow at a compound annual growth rate (CAGR) of 2.5% from 2020 to 2027.
The rising consumption of dairy products and shifting consumer preference from meat to
dairy products for protein enrichment are the significant drivers for this market’s growth.
The easy availability of dairy products due to modern retail facilities and cold chain logistics
further drives the market growth. Furthermore, significant product sales through online
distribution channels during the Covid-19 pandemic also supported the market growth.
Fig: The Diary product market size,by product (2016-27).
Market Dynamics
Fig: Dairy Vs Dairy free products.
The nutritional benefits offered by dairy products is the major driver for the growth of the
global dairy products market. The rich content of vitamins, minerals, and proteins present in
milk made dairy an essential food for humans. For instance, the calcium content of milk
helps develop healthy bones and teeth among young children, thus making it a vital part of
infant nutrition. Furthermore, vitamin D reduces the risk of cancer protection, potassium
helps reduce the levels of blood pressure and improves heart health, and fermented milk
acts as a probiotics source for improving gut health.
The high nutritional value of fermented dairy products is motivating the sales of Yogurt
Cheesecakes and other dairy based desserts. Other factors responsible for the growth of
dairy market include rising consumer spending, growing population and consumer
preference for nutritional rich food products. However, the rise in veganism and plant-based
eating preferences of vegetarian population is limiting the consumption of dairy products.
Lactose intolerance, dairy sensitivity, consumer shift towards plant-based food products,
and misconceptions associated with consumption of milk are other key restraints of the
market.
However, recent studies have shown that cheese is good for heart health and could be an
excellent source of calcium for people with lactose intolerance. Growing focus on infant
nutrition and demand for organic clean label dairy products are also expected to boost the
market growth. The market has several growth opportunities, as consumers are willing to
try new products.
Innovation in yogurts, such as fat-free, flavored, and drinkable yogurt, is expected to provide
the manufacturers with significant growth opportunities. Innovation in the packaging, such
as small portion size, on-the-go packs, and single-serve, is also driving the product demand,
providing a massive opportunity to the manufacturers.
India has always been the largest producer (an estimated 400 million litre per day currently)
and consumer of milk in the world. But it remained a boring market largely because the per
capita consumption was low, and most of the milk was consumed in its basic, liquid form,
or at best as ghee and some butter.
Out of the 400 million litres of milk that India produces per day, 160 million litres per day (48
per cent) is retained by the producers for their own consumption. The surplus milk that is
available for sale is around 240 million litres per day, and out of that only 70 million litres per
day is being used by the organised sector – consisting of co-operatives such as Amul,
Mother Dairy and Nandini (a brand owned by the Karnataka Cooperative Milk Producers
Federation (KMF), as well as private sector players such as Nestle and Danone. Over 170
million litres of the surplus milk continues to be with the unorganised sector, comprising
traditional domestic. In value terms, the Indian milk economy is worth Rs 5 lakh crore,
growing at a CAGR of 15-16 per cent, out of which the organised milk economy is worth Rs
80,000 crore.
Market Segmentation
The global dairy products market has been segmented by product type covering milk,
cheese, butter, whey protein, milk powder, and various other dairy products. Liquid milk is
the major dairy food and the demand for liquid milk products is rapidly surging with the
rising health consciousness and living standards of the consumers. Infants are the major
promoters of the milk market in the form of infant formula and baby milk. The global market
for infant nutrition reached 2.5 million tons in 2017 and is likely to witness over 7% growth
rate in the next decade. The growing supply of milk is also supporting the growth in this
segment. According to the statistics of The Food and Agriculture Organization of the United
Nations (FAO), global milk production witnessed a growth of 58% in the last three decades
and reached 828 million tons in 2017. In most of the countries including highly populous
India and China, milk is considered as a major part of healthy dietary protocol.
Liquid milk accounts for over 90% of the demand for dairy products in rural areas and over
85% of that in urban areas in India. Supermarkets and hypermarkets evolved as the largest
sales channel for dairy products with a share of nearly 50% in terms of sales value in 2018.
The growing retail sales of dairy products in Asian countries owing to ‘go to retail market’
strategy of manufacturers to reach retail stores is motivating the sales through
supermarkets and hypermarkets. For instance, Parag Milk Foods Company in India is
planning to widen its retail distribution network by 3x times in the next six years.
Convenience stores, specialty stores, and e-commerce are also holding a significant share
in the sales of dairy products.
Distribution Channel Insights
The supermarkets/hypermarkets segment accounted for the largest revenue share of over
60% in 2019. A rise in the number of supermarkets/hypermarkets and the availability of a
wide range of products in such stores are the primary factors driving the segment growth.
Supermarkets have controlled temperature shelves for dairy products to avoid any spoilage.
Consumers find it convenient to buy daily needs at lower prices in these stores, which is
likely to drive the segment growth significantly in the coming years.
The online segment is expected to ascend at the fastest CAGR over the forecast period due
to the convenience offered by these distribution channels. Some of the popular online
distribution channels for dairy products include Just Milk, Sainsbury’s, Ocado, Mr. Case, and
Walmart. Some companies also deliver the product online through their mobile application.
For instance, India-based GCMMF (Amul) delivers milk and other dairy products via its
mobile application. The growing usage of the internet and improved connectivity across the
world will also augment the segment growth.
Situational Analysis
Environment
The situation analysis is required prior to setti ng up a marketing strategic plan. The culture
of food delivery and ordering online is growing at an unimaginable rate.
Food delivery is more common to serve dairy products if it’s a busy city.
Current Trend in the Food Delivery Industry
1. More consumers will order food online and at a higher frequency
In this century, due to busy schedules and heavy traffic, ordering online has become so
normal and easy for consumers that we only expect the growth and frequency of that trend
to increase.
2. Technology will continue to propel the industry forward
Technology is the lifeblood of every industry, and with modern users’ digital expectations,
alongside fierce competition in the food delivery industry, new and creative use of
technology is the only way to succeed. With the high usage of smartphones, consumers
prefer to order their food via the online services by downloading apps and choosing their
favourite food.
3. Variations in the Common Delivery Model
As soon as a new trend is adopted by certain key players in the industry, others will follow
suit.
4. In-house and third party delivery services will compete fiercely
The rise of third party delivery services like foodpanda, UberEATS and DeliverEAT have
undoubtedly disrupted the food delivery space, in the same way Uber and Airbnb have
shaken up the traditional business models of taxi firms and hotels.
TARGET MARKET
The target market of food delivery service startups can be categorized in terms of
demographic, behavioural and psychographic.
With an increasing number of people being productively employed in lucrative industries,
they have increased their living standards and made their wallets fatter too. The target
group are mainly the middle income segment who have a higher disposable income.
Food Delivery Service Company targets the population in urban and semi urban locations
because the city dwellers have a very busy life. The customers need to keep up with the
hectic schedule and they need immediate, reliable and assistance for their day-to-day tasks.
Urban and semi urban locations are ideal and potential market segment due to increasing
internet penetration & rapid smartphone adoption,
Behavioural
The target market can be divided into two segments which are advocates and pragmatic.
Owns a mobile
Whether consumers want to find/order a product, takeaway or have delivered, increasingly
the tool of choice is the mobile phone. Mobile apps and web based system play an
important role in food ordering at this point of time . With more people using smart phones,
increasing literacy and access to the Internet, it is highly recommended for food delivery
business to leverage on this new opportunity.
Has good experience with online purchasing
The menu will be offered in multiple online platforms and they are familiar with apps. The
customers should be familiar with the functions of the apps and the process of making
online orders.
Loyal Customers
Customers who will stay with one food delivery company if they are efficiently served
Influential
Bloggers, Food critics
Pragmatic
The pragmatic group of customers are always finding the best option to have their food
delivered. They are usually not loyal to one particular food delivery company hence they will
order food from other food delivery companies and might switch from other food delivery
companies due to poor service. They are the type of customers who wish to order food to
save cost and time
Psychographic
Achievers
1. Are fully scheduled
Customers have limited time to spend and will choose to have a pre allocated delivery i.e.,
mostly based on the schedule they have provided.
2. Are goal oriented and hardworking
Customers have datelines to catch up hence food delivery will be of convenience
3. Are peer conscious
Customers who order food if their colleagues are doing the same
4. Value technology that provides a productivity boost
Customers who wish to make full use of the technology to compare menus, price and
reviews before purchasing
Experiencers
1. Are first in and first out of trend adoption
Customers who wishes to try out a new service especially if it is trending
2. Want everything
Customers who wants to subscribe to online food delivery services if their peers do
3. Go against the current mainstream
Customers who are longing to try something fresh and new,e.g idea or services
4. Are spontaneous
Customers who do not plan their orders and will spontaneously decide to order upon
noticing an advertisement
5. Have a heightened sense of visual stimulation
Customers who are attracted to gorgeous visuals of food on advertisements
Demographic
Demographic segmentation groups customers and potential customers together by
focusing on certain traits such as age, gender, income, occupation & family status. ... There
are plenty of ways to segment markets using demographics. The most commonly used
demographic segmentation factors are: Age.Age, Gender, Education, Ethnicity, Income,
Employment, hobbies, etc.
Pros of demographic segmentation
1. Easy to find: It is accessible and easy to use. For example, government censuses are
available in most countries.
2. Identify potential market: When an organization looks at the demographic segmentation,
it focuses on the people who are most likely to buy a product. This helps in identifying the
target market.
3. Marketing: Demographic customer segmentation helps organizations in developing
market outreach for better marketing strategies.
Cons of demographic segmentation
1. Assumptions: Demographic segmentation is based on the assumption that consumers in
the same demographic group will have similar needs.
For example; not everyone in their 30s will have the same needs when it comes to buying a
mobile phone. Some might want a high-resolution camera, others might want storage
capabilities, better speakers, etc.
2. Constant changes: Behavior is never constant. Marketers cannot collect demographic
data once, and use that same information for years. Because the population changes.
Census data is updated every year. This information must be collected constantly to get a
real scenario.
Geographic
It is a component that competently complements a marketing strategy to target products or
services on the basis of where their consumers reside. Division in terms of countries,
states, regions, cities, colleges or Areas is done to understand the audience and market a
product/service accordingly.
Advantages of Geographic Segmentation
● Enhanced focus due to targeting: Geographic segmentation is an effective method
to improve focus on target audience. As a division based on geographical
characteristics is involved, organizations tend to create more focused marketing
strategies to convert local consumers into successful customers.
● Immediate market growth: In situations where an organization has a marketing
strategy for a particular location, it becomes additionally convenient for this
organization to apply the same strategy to neighboring locations which demonstrate
similar geographical characteristics. Expanding marketing operations and
developing corresponding strategies for locations with unknown characteristics is
much more time and resource consuming than expanding to locations that indicate
traits similar to the existent target market.
● Improved communication: As targeting is based on geography and the traits that
change with a change in geographies, marketing and promotional communications
for local audiences need to be according to the specialized nature of this
geographical segment. Better communication happens when there’s clarity in
regards to what the audience expects out of a product/service.
● Increase profits: Geographical segmentation gives an organization an essential early
competitive edge in localized markets, increases brand recall value and also helps in
providing better customer service which in turn leads to better customer retention
rates. For organizations that have limited reach, geographic segmentation is a
strategy to focus their resources on accurate target audiences and receive better
revenue results.
How Does Geographic Segmentation Work?
Geographic segmentation is all about grouping target consumers based on their shared
geographical characteristics. The core assumption of geographic segmentation is that a
consumer’s needs and wants can vary based on their location, and that grouping people by
location can help marketers deliver more relevant content that addresses the needs of
consumers in a specific place. There are several geographical parameters that can be used
to identify and delineate customer segments in order to deliver more targeted
advertisements.
Analysis and Approaches used for Segmentation
Clustering
Clustering is one of the most common exploratory data analysis techniques used to get an
intuition about the structure of the data. It can be defined as the task of identifying
subgroups in the data such that data points in the same subgroup (cluster) are very similar
while data points in different clusters are very different. In other words, we try to find
homogeneous subgroups within the data such that data points in each cluster are as similar
as possible according to a similarity measure such as euclidean-based distance or
correlation-based distance. The decision of which similarity measure to use is
application-specific.
Clustering analysis can be done on the basis of features where we try to find subgroups of
samples based on features or on the basis of samples where we try to find subgroups of
features based on samples.
K Means Algorithm
K Means algorithm is an iterative algorithm that tries to partition the dataset into
pre-defined distinct non-overlapping subgroups (clusters) where each data point belongs to
only one group. It tries to make the intra-cluster data points as similar as possible while
also keeping the clusters as different (far) as possible. It assigns data points to a cluster
such that the sum of the squared distance between the data points and the cluster’s
centroid (arithmetic mean of all the data points that belong to that cluster) is at the
minimum. The less variation we have within clusters, the more homogeneous (similar) the
data points are within the same cluster.
The way k means algorithm works is as follows:
1. Specify number of clusters K.
2. Initialize centroids by first shuffling the dataset and then randomly selecting K data
points for the centroids without replacement.
3. Keep iterating until there is no change to the centroids. i.e assignment of data points
to clusters isn’t changing.
The approach k-means follows to solve the problem is expectation maximization
The E-step is assigning the data points to the closest cluster. The M-step is computing the
centroid of each cluster. Below is a break down of how we can solve it mathematically
The objective function is:
And M-step is:
Applications
K means algorithm is very popular and used in a variety of applications such as market
segmentation, document clustering, image segmentation and image compression, etc. The
goal usually when we undergo a cluster analysis is either:
1. Get a meaningful intuition of the structure of the data we’re dealing with.
2. Cluster-then-predict where different models will be built for different subgroups if we
believe there is a wide variation in the behaviors of different subgroups.
Implementation
Data Sources
We have gathered some datasets which are somehow related to the case.
Packages/ Tools used:
1. Numpy : To calculate various calculations related to arrays.
2. Pandas : To read or load the datasets.
We have considered two datasets for the analysis.
1. It is a survey result of the customers preference and reviews on online food
delivery who are residing in Bangalore.
df = pd.read_csv('data.csv')
df.head(3)
2. It’s datasets of the segment analysis of an online delivering company.
tf = pd.read_csv('data2.csv')
tf.head(3)
Data Pre-processing
Tools used :
1. SkLearn : We have used LabelEncoder() to encode our values.
Changing the categorical object into numerical values
We have used the LabelEncoder of sklearn package to encode our data or objects into
some integral values.
le_gender = LabelEncoder()
le_gender.fit(['Female','Male'])
df.iloc[:,1] = le_gender.transform(df.iloc[:,1])
le_marital = LabelEncoder()
le_marital.fit(['Single', 'Married','Prefer not to say'])
df.iloc[:,2] = le_marital.transform(df.iloc[:,2])
le_occupation = LabelEncoder()
le_occupation.fit([ 'Student', 'Employee','Self Employed','House wife'])
df.iloc[:,3] = le_occupation.transform(df.iloc[:,3])
df.head(3)
##---------------------------
for i in ['Gender' , 'Ever_Married' ,
'Graduated','Profession','Spending_Score','Var_1' ]:
le = LabelEncoder()
tf[i] = le.fit_transform(tf[i].astype('str'))
tf[0:5]
Handling the null values
print("------Dataset 1---------")
print(df.isnull().sum().sort_values(ascending=False)[1:] / 388 * 100)
print("------Dataset 2---------")
print(tf.isnull().sum().sort_values(ascending=False)[1:] / 8068 * 100)
We have some null values in dataset2 but 0 in dataset 1.
We will handle the null values by replacing with mode.
Removing duplicates
print('Duplicated value(s) on the dataset1 : ', df.duplicated().sum())
print('Duplicated value(s) on the dataset2 : ', tf.duplicated().sum())
As we can see we have some duplicates in dataset 1, we will remove the duplicate
entries.
data.drop_duplicates(keep="first", inplace=True)
Analysis
Demographic Analysis
plt.figure(figsize=(10,6))
sns.countplot(x="Age", data=df, hue='Output')
Here we can see that the customers above 26 years of age are most likely to get churn. And
the optimal target age group should be 21 to 28.
If we analyse the spending nature then,
plt.figure(figsize=(20,6))
sns.countplot(x="Age", data=tf, hue="Spending_Score")
Here we observed that the spending of younger customers is low compared to the elder
customers.
If we analyse the spending score vs family size , we can see
plt.figure(figsize=(10,6))
sns.countplot(x="Family_Size", data=tf, hue="Spending_Score")
Clearly we can see customers having 2 to 5 family members have good spending scores
compared to singles which have low spending scores which is understandable.
Geographic Analysis
As we don’t have a good datasets to describe geographic segmentation so, we have
considered the customer churn datasets where we are analysing the location with the ease
and convenience question
We have considered only the age_band of 18 to 40.
Fig: geographic Analysis
Here red represents disagreement and green represents agreement.
Since majority are in agreement of the online delivery so the company will have no problem
in choosing bangalore as their first market place.
Psychographic Analysis
Here we took dataset 1 and have plotted different survey questions related to online food
delivery.
Here we can analyse all the preferences and reviews of the customers on various aspects
of a company.
Fig: Reviews of users
Fig: Reviews of users
Behavioral Analysis
If we look into the behavioral aspect then we can see that,
sns.countplot(x="Graduated", data=tf, hue="Spending_Score")
We can see that usually graduates have more tendency to spend more which is obviously
logical.
plt.figure(figsize=(10,6))
sns.countplot(x="Work_Experience", data=tf, hue="Spending_Score")
Here we can observe that the customers whose experiences are high are relatively low
in numbers in contributing to the purchases.
Segmentation
Using K Means
Age and Spending Score:
clus = tf.loc[:,["Age","Spending_Score"]].values
And we can use the Elbow method to find the optimum K value.
For this our plot is something like this.
Here we can see that after 2 the slope is increasing rapidly so we can assume K to be
equal to 2.
kmeans = KMeans(n_clusters=2, init='k-means++', random_state=42)
Y = kmeans.fit_predict(clus)
Now we can plot the Y to differentiate our clusters.
Family size and Profession:
clus = tf.loc[:,["Family_Size","Profession"]].values
plotElbow2d(wcss)
This also doesn't help that much.
Age, family size and segmentation variable:
Now considering 3 features we plot the elbow curve.
This is the following Elbow plot.
These will be the two required clusters.
Age, family size and spending score:
Now considering 3 features we plot the elbow curve.
Here we can take k=2, k=3
Now if we plot using 3 features we get a 3d plot.
Here we can see 3 clusters based on ages, family members and spending
behaviours.
Target segment
So from the analysis we can see that the optimum customer base or the targeted
customers should be of age bracket [20-35] with family members more than 1 and if
graduate is a plus.
Marketing Mix
Setting prices for our products is both an art and a science. Most importantly, you
must know and understand your cost of production. From there you can adjust
based on product characteristics, a specific pricing strategy, customer price
sensitivity, customer values, and other factors. Price contributes to the perception of
your product, that is, when consumers see a product price it sends signals to them
about quality, match with the market outlet, expectations for assistance, etc. Keeping
accurate and complete records accounting for all steps – production, packaging,
storage, promotion, transportation/distribution, and sales – will assist you in setting
a price and making adjustments as necessary.
4Ps of Marketing Mix
The 4Ps helps companies to review and define key issues that affect the marketing of its
products and services and is often now referred to as the 7Ps framework for the digital
marketing mix.
Marketing as a whole relies on all seven Ps.
It is essential to consider them as a whole, and not in isolation. Customers must experience
a coherent view of your company and your product, and that can only come from viewing
the customer experience from end-to-end across all seven Ps.
Importance of Marketing Mix
It helps understand what our product or service can offer to our customers and helps plan a
successful product offering. Helps with planning, developing and executing effective
marketing strategies. Help determine whether your product or service is suitable for your
customers.
Product: Since the company is starting with the dairy product so we can’t comment
about the product.
Price:-As we have dairy products only so their price would be according to the
availability from the source and price may vary as the market goes up or down.
Place:- Through the analysis we have seen that bangalore is the best suitable for any
startup or online goods delivering company.
Promotion: Promotion can be based on the analysis. More offers and promotions can
be given to the segments that are more valuable to the company.
Codes
All the codes used in this project can be found on
https://github.com/SasukeUchiha7/market-segmentation
References
Datasets that has been used in this project are taken from
https://www.kaggle.com/datasets
