SUMMER INTERNSHIP PROJECT REPORT

On

―THE SALES ANALYSIS OF PATANJALI AN PREDICTING THE

SALES FOR FUTURE USING POWER BI”

By
SHRUTI RAJESH GODGHATE
Institute Roll Number: 20220143055
MBA III - BUSINESS ANALYTICS

Under the guidance of

Dr. ANAGHA VAIDYA
Submitted to

Savitribai Phule Pune University

In partial fulfillment of the requirement for the award of the degree of
Master of Business Administration (MBA)
2023-24

Through

Suryadatta Education Foundation’s

Suryadatta Institute of Management & Mass Communication (SIMMC)
Pune- 411021

1
 DECLARATION

I am SHRUTI RAJESH GODGHATE a student of MBA , 2nd Year

at, Suryadatta Institute of Business Management & Mass Communication.

Project work titled Financial Analytics in Power BI

Submitted by me to SAVITRIBAI PHULE PUNE UNIVERSITY, PUNE

I hereby declare that the project presented in this summer internship

report is my own work done by me.

Place: Pune Name : SHRUTI RAJESH GODGHATE

Sign:

2
 ACKNOWLEDGEMENT
It is a great pleasure for me to acknowledge my deep sense of gratitude to
all those who have helped me in completing this project successfully. First and
foremost, I would like to thank Savitribai Phule Pune University for providing
me with the opportunity to undertake this project as a partial fulfillment of my
MBA degree.

I would like to express my sincere gratitude to everyone who helped me

during my summer internship at Movidu Technologies Pvt Ltd, Bengaluru.

I would like to thank my supervisor, for their guidance, support, and

encouragement throughout the internship. I am grateful for their willingness to
share their knowledge and expertise with me, and for helping me to develop my
skills and abilities.

I would also like to thank Movidu technologies pvt LTD for their help
and cooperation throughout my internship. I am grateful for the warm and
welcoming environment they created, and for their willingness to answer my
questions and provide me with feedback.

This project report could not have been completed without the guidance
of my project guide Dr. Anagha Vaidya whose valuable encouragement at
every phase has help me to prepare this Project successfully.

Place: Pune Name: SHRUTI RAJESH GODGHATE

Sign:

3
 INDEX

CHAPTER PAGE
CHAPTER NAME
NO. NO.

EXECUTIVE SUMMARY

1 INTRODUCTION

2 LITERATURE REVIEW

3 INDUSTRY & COMPANY PROFILE

4 RESEARCH METHODOLOGY

5 DATA ANALYSIS & INTERPRETATION

6 CONCLUSION

7 SUGGESTION

8 BIBLIOGRAPHY

9 ANNEXURE

4
INTRODUCTION

5
 INTRODUCTION
Sales forecasting has always been a very significant area to concentrate upon. An efficient
and optimal way of forecasting has become essential for all the vendors in order to sustain the
efficacy of the marketing organizations. Manual infestation of this task could lead to drastic
errors leading to poor management of the organization, and most importantly would be time
consuming, which is something not desirable in this expedited world. A major part of the
global economy relies upon the business sectors, which are literally expected to produce
appropriate quantities of products to meet the overall needs.

Targeting the market audience is the major focus of business sectors. It is therefore important
that the company has been able to achieve this objective by employing a system of
forecasting. The process of forecasting involves analyzing data from various sources such as
market trends, consumer behavior and other factors. This analysis would also help the
companies to manage the financial resources effectively. The forecasting process can be used
for many purposes, including: predicting the future demand of the products or service,
predicting how much of the product will be sold in a given period. This is where machine
learning can be exploited in a great way. Machine learning is the domain where the machines
gain the ability to outperform humans in specific tasks.

They are used to do some specialized task in a logical way and gain better results for the
progress of the current society. The base of machine learning is the art of mathematics, with
the help of which various paradigms can be formulated to approach the optimum output. In
case of sales forecasting also machine learning has proved to be a boon.It is helpful in
predicting the future sales more accurately. In our paper we have proposed the machine
learning algorithms towards the data collected from the previous sales of a grocery store. The
objective here is to envisage the pattern of sales and the quantities of the products to be sold
based on some key features gathered from the raw data we have. Analysis and exploration of
the collected data has also been done to gain a complete insight of the data. Analysis would
help the business organizations to make a probabilistic decision at each important stage of
marketing strategy.

6
INTRODUCTION TO DATA MINING ALGORITHM

A facts mining algorithm is a hard and fast of heuristics and calculations that creates a
information mining model from information. To create a version, the algorithm first analyzes
the records provided , searching out unique styles of styles or trends. The set of rules makes
use of the consequences of this analysis to outline the most appropriate parameters for
creating the mining model. These parameters are then applied across the complete
information set to extract actionable patterns and certain facts. The statistics mining model
that an set of rules creates from your records can take numerous paperwork, together with:
Measuring Efficiency of an Algorithm :

 A fixed of clusters that describe how the instances in a dataset are associated.

 A decision tree that predicts an outcome, and describes how unique criteria have an
effect on that final results.
 A mathematical version that forecasts income.

 A fixed of guidelines that describe how products are grouped together in a

transaction, and the probabilities that products are bought collectively.
Statistics Mining Algorithms:

Several center strategies that are used in data mining describe the form of mining and data
restoration operation:
 Type algorithms are expecting one or more discrete variables, primarily based on the
other attributes within the dataset.
 Regression algorithms are expecting one or more continuous variables, which
includes income or loss, primarily based on other attributes in the dataset.
 Segmentation algorithms divide statistics into companies, or clusters, of objects which
have comparable residences.
 Association algorithms find correlations between exceptional attributes in a dataset.
The maximum common application of this sort of algorithm is for developing
association guidelines, which may be utilized in a market basket evaluation.
 Series analysis algorithms summarize frequent sequences or episodes in statistics,
together with an internet path drift.

7
Classification Algorithm

Class is the procedure of locating a version (or function) that describes and distinguishes
information instructions or concepts. The model are derived based totally on analysis of a set
of education statistics (The statistics gadgets for which the elegance labels are known). The
version is used to are expecting the class label of objects for which the class label is
unknown.
The derived model may be represented in numerous paperwork including classification
guidelines (i.E. IF…THEN policies) , decision trees , Mathematical formulae or Neural
Networks. Type may be used to accumulate an concept of the kind of purchaser, item, or
object by using describing a couple of attributes to discover a specific magnificence. As an
instance, we will easily classify automobiles into different types (sedan, 4x4, convertible)
through figuring out extraordinary attributes (number of seats, car shape, driven wheels).
Given a new automobile, we'd observe it into a particular magnificence through comparing
the attributes with our recognised definition. We are able to follow the identical principles to
clients, for example by way of classifying them with the aid of age and social institution.
Type predicts specific (discrete , unordered) labels while regression evaluation is a statistical
methodology that is most usually used for numeric prediction. Clustering lets in to use not
unusual attributes in exceptional classifications to pick out clusters.

8
PROPOSED SYSTEM

Target promoting is a common case of a gauge issue. Data mining utilizes verifiable portrayal
data to recognize focuses on that are well on the way to expand degree of profitability in
future focusing on. In contrast to different algorithms, O-DAM [Optimized Distributed
Association Rule Mining] attempts to work better by limiting the arrangement of requester
components. It does this by drawing in two principle D- ARM [distributed affiliation rule
mining] issues: intercommunication and coordination. Radio is probably the best goal of D-
ARM. The D-ARM algorithm works best on the off chance that it can decrease radio. D-
ARM finds rules for various topographically doled out data sets. Be that as it may, the
system associations between these data sets are not as quick as in an equal domain, so alloted
mining by and large intends to limit correspondence costs. Intended to work with records.
The algorithm finds a typical subset of in any event the base number C of thing sets (breaking
point or certainty edge).
The proposed framework expect that the organization's three branches and its regarded
branch administrator can get to the branch database and find shrouded designs in the
database. Rather than having three databases at each branch that store all organization
records, there is a focal server, kept up by an overseer. A fascinating inquiry is the thing that
entrance to make. The two directors and heads can change the data. That is, you can include
and erase records in the database. To discover concealed examples in the database, they
utilize a framework that actualizes a from the earlier algorithm to discover visit things in the
database and can see the yield as reports and pie diagrams. Pie outlines are utilized for a
superior comprehension. In this way, the supervisor of each branch can locate the successive
things in that branch, since the overseer needs to settle on significant choices about the
organization, and the manager can see or search the regular things in all the branches.

9
VISUAL STUDIO

Microsoft Visual Studio is an integrated development environment (IDE) from Microsoft. It

is used to develop computer programs, as well as websites, web apps, web services
and mobile apps. Visual Studio uses Microsoft software development platforms such as
Windows API, Windows Forms, Windows Presentation Foundation, Windows Store and
Microsoft Silverlight. It can produce both native code and managed code.
Visual Studio includes a code editor supporting IntelliSense (the code completion
component) as well as code refactoring. The integrated debugger works both as a source-level
debugger and a machine-level debugger. Other built-in tools include a code profiler, designer
for building GUI applications, web designer, class designer, and database schema designer. It
accepts plug-ins that enhance the functionality at almost every level— including adding
support for source control systems (like Subversion and Git) and adding new toolsets like
editors and visual designers for domain-specific languages or toolsets for other aspects of the
software development lifecycle (like the Azure DevOps client: Team Explorer).
Visual Studio supports 36 different programming languages and allows the code editor and
debugger to support (to varying degrees) nearly any programming language, provided a
language-specific service exists. Built-in languages include C, C++, C++/CLI, Visual Basic
.NET, C#, F#, JavaScript, TypeScript, XML, XSLT, HTML, and CSS. Support for other
languages such as Python, Ruby, Node.js, and M among others is available via plug- ins. Java
(and J#) were supported in the past.
The most basic edition of Visual Studio, the Community edition, is available free of
charge. The slogan for Visual Studio Community edition is "Free, fully-featured IDE for
students, open-source and individual developers".
The currently supported Visual Studio version is 2019.

FEATURES

Like any other IDE, it includes a code editor that supports syntax highlighting and code
completion using IntelliSense for variables, functions, methods, loops,
and LINQ queries. IntelliSense is supported for the included languages, as well asfor
XML, Cascading Style Sheets, and JavaScript when developing web sites and web
applications. Autocomplete suggestions appear in a modeless list box over the code editor
window, in proximity of the editing cursor. In Visual Studio 2008 onwards, it can be made

10
temporarily semi-transparent to see the code obstructed by it. The code editor is used for all
supported languages.
The Visual Studio code editor also supports setting bookmarks in code for quick navigation.
Other navigational aids include collapsing code blocks and incremental search, in addition to
normal text search and regex search. The code editor also includes a multi- item clipboard
and a task list. The code editor supports code snippets, which are saved templates for
repetitive code and can be inserted into code and customized for the project being worked on.
A management tool for code snippets is built in as well. These tools are surfaced as floating
windows which can be set to automatically hide when unused or docked to the side of
the screen. The Visual Studio code editor also supports code refactoring including
parameter reordering, variable and method renaming, interface extraction, and
encapsulation of class members inside properties, among others.
Visual Studio features background compilation (also called incremental compilation). As
code is being written, Visual Studio compiles it in the background in order to provide
feedback about syntax and compilation errors, which are flagged with a red wavy underline.
Warnings are marked with a green underline. Background compilation does not generate
executable code, since it requires a different compiler than the one used to generate
executable code. Background compilation was initially introduced with Microsoft
Visual Basic, but has now been expanded for all included languages.

11
MICROSOFT SQL

Microsoft SQL Server is a relational database management system developed by

Microsoft. As a database server, it is a software product with the primary function of storing
and retrieving data as requested by other software applications—which may run either on the
same computer or on another computer across a network (including the Internet). Microsoft
markets at least a dozen different editions of Microsoft SQL Server, aimed at different
audiences and for workloads ranging from small single-machine applications to large
Internet-facing applications with many concurrent users.
Data storage is a database, which is a collection of tables with typed columns. SQL Server
supports different data types, including primitive types such as Integer,
Float, Decimal, Char (including character strings), Varchar (variable length character strings),
binary (for unstructured blobs of data), Text (for textual data) among others. The rounding of
floats to integers uses either Symmetric Arithmetic Rounding or Symmetric Round Down
(fix) depending on arguments: SELECT Round(2.5, 0) gives 3.
The SQL Server Machine Learning services operates within the SQL server instance,
allowing people to do machine learning and data analytics without having to send data across
the network or be limited by the memory of their own computers. The services come with
Microsoft's R and Python distributions that contain commonly used packages for data
science, along with some proprietary packages (e.g. revoscalepy, RevoScaleR, microsoftml)
that can be used to create machine models at scale.

12
Feasible Study

A Feasibility Study determines whether a project is worth doing. The process followed for
making this determination is called a Feasibility Study. This type of study determines
whether a project can and should proceed. Once it has been determined that a project is
feasible, the analyst can proceed and prepare the project specifications that finalize the project
specification. The following are the various types of feasibility studies that can be
undertaken.

Technical Feasibility

This is concerned with specifying the equipment and the software to satisfy the user
requirements. The technical needs of the system vary considerably butmight include:

Technical feasibility centers on the existing computer system, hardware, software etcetera
and to what extent it can support the system. In examining the technical feasibility, the
configuration of the system is given more importance than the actual hardware. The
configuration should provide the complete picture of the system requirements, for example
how many workstations are required and how these units are interconnected so that they
would operate smoothly, etcetera. The result of the Technical Feasibility Study is the basis
for the documents against which dealer and manufacturer can make bids. Specific hardware
and software products can then be evaluated keeping in view thelogical needs.

Economic Feasibility

Economic analysis is the most frequently used method for evaluating the effectiveness of a
new system. More commonly known as cost/benefit analysis, the procedure is to determine
the benefits and savings that are expected from a candidate system and compare them with
costs. If benefits outweigh costs, then the decision is made to design and implement the
system. It is not done to analyze the new system. Using a Gantt chart schedule and part
chart.We assumed that the benefit of the project is greater than the cost. So if we can develop
the project easily then it is used for the evaluation of the proposed. We calculate the
cost/benefit analysis and we assume that the benefit is feasible so we start developing the

13
project. It is an analysis of the cost to be incurred in the system and benefits the derivable
from the system. An economic Feasibility Study should demonstrate the net benefit of the
proposed course of action in the context.

Behavioral Feasibility

Normal psychology of human beings indicate that people are resistant to change and
computers are known to facilitate change. Any project formulations should consider this
factor also. Before the development of the Project titled "Delhi Metro", the need to study the
feasibility of the successful execution of the project was felt and thus the following factors
are considered for a Feasibility Study. Need Analysis. Provide the users information
pertaining to the preceding requirement.‘
Operational Feasibility

It determines how acceptable the software is within the organization. The evaluations must
then determine the general attitude and skills. Such restriction of the job will be acceptable.
To the users are enough to run the proposed budget, hence the system is supposed to the
feasible regarding all except of feasibility. In operational feasibility, we attempt to ensure that
every user can access the system easily. We develop a menu that users can easily access and
we provide shortcut keys. We show a proper error message when any mistakes are made in
the program. We provide help and a guideline menu to help the user. Changes in the ways
individuals are organized into groups may then be necessary and the groups may now
compete for economic resources with the needs of stabilized ones by converting a number in
a file in software

Feasibility Study Report

The result of the Feasibility Study provides us with the following facts:
 This system would increase the efficiency of the system. This system would
increase customer's satisfaction.
 This system has many requirements such as Efficiency cost effectiveness, prompt
service, Reliability.
 This system would add to the security features of the system
 This system should be simple to use, incorporate all necessary services and
maintainable

14
The Fast Moving Consumer Goods (FMCG) sector is the fourth largest sector in Indian
economy. Food product is the leading segment accounting more than 53% in this sector.
Personal care 20% and fabric care 10% come next in term of market share. It has a strong
MNCs presence and is characterize by well established distribution network, intense
competition between organized and unorganized segments and low operational cost.
Availability of key raw material, cheap labour and presence across the entire value chain
gives India a competitive advantage.

The penetration of FMCG in rural area is not high as yet but the opportunity of growth in this
area is huge by means of enhanced penetration into the rural market and conducting the
awareness programme in this area. The scope of growth of FMCG sector is high as per capita
consumption of FMCG products is low in comparison to the developed countries.

The major players in FMCG sector in India are; Hindustan Unilever, Procter &
Gamble(P&G), Dabur India ltd, Colgate-Palmolive India, Coca Cola, Pepsico Ind., Nestle,
Britannia India Ltd. and most of them are foreign MNCs. In other word we can say that
Indian FMCG sector is ruled by the foreign companies and huge amount of revenue are
drained to the foreign countries.

Patanjali –From Yoga-Shastra to Artha-Shastra (Yoga to Economics), Company Profile

at a Glance:

Acharya Balkrishna established Patanjali Ayurved ltd in the year 2006 along with Baba
Ramdev with the objective of establishing science of ayurveda in accordance and
coordinating the latest technologyand ancient wisdom. Patanjali Ayurved Ltd is a complete
Indian FMCG company located in the industrial area of Haridwar(U.K),India. According to
CLSA( Credit Lyonnais Securities Asia) and HSBC , Patanjali is a fastest growing FMCG
company in India. Its asset value goes up to Rs13000Cr and some predicted revenue of rupees
5000 crores for the fiscal year 2015-16.

Patanjali food and herbal park at Hardwar is the main production facility operated by
Patanjali Ayurved. The company plans ato established further units in India and Nepal in near
future. It produces products in the category of personal care and food sector. The company
produces 444 types of products including 45 types of cosmetics products 30 types of food
products. According to the company all the products manufactured by Patanjali are made
from Ayurveda and natural components.

15
Movidu Technologies Pvt. Ltd.products are cheaper compare to the alternatives available in
the market due to less production and marketing cost. It has also launched beauty and baby
products. Its ayurvedic manufacturing division has over 300 medicines for treating a range of
ailments and body condition from common cold to chronic paralyses.

Patanjali launched instant noodles on 15th November 2015 after the Maggi controversy,
which has a market share of 77% in noodles sector, with the aim to capture world 5th largest
noodles market worth more than 4000 Crore.

Patanjali sales it‘s products nearly through 4000 outlets as on 2015. It also sells its products
through online and planning to open outlets in Railways Stations and Airports.

It also has tied up with Pittie and Kishore Biyani‘s Future Group on oct.9, 2015, to make
available its products in all the outlets of Future Groups.

Its products are also available in modern trade centre like Reliance Retail, Hyper City, and
Star Bazaar apart from online channels. Defense organization, DRDO entered into licencing
agreements with Patanjali Ayurveda for transfer of technology.

16
COMPANY PROFILE

17
 COMPANY PROFILE

COMPANY NAME - MOVIDU TECHNOLOGIES PVT. LTD

Movidu Technology Private Limited is a Private incorporated on 04 October 2021. It is

classified as Non-govt company and is registered at Registrar of Companies, Bangalore. Its
authorized share capital is Rs. 1,500,000 and its paid up capital is Rs. 500,000. It is inolved in
Higher education [Includes post-secondary/senior secondary sub-degree level education that
leads to university degree or equivalent.]

Movidu Technology Private Limited's Annual General Meeting (AGM) was last held on N/A
and as per records from Ministry of Corporate Affairs (MCA), its balance sheet was last filed
on 31 March 2022. Directors of Movidu Technology Private Limited are Mridula Bhupendra
Chhetri and Pushp Raj Singh.

OUR FOUNDERS

Mridula Chhetri Haas School of Business

Co-founder comes with a decade + of experience in working with startups and multinational
companies from all around the world. She's a results-driven professional with a global
exposure, international and entrepreneurial experience in business strategy, product
development, strategic marketing in shared economy sector. Now she's building India's
largest student workforce!

Pushpraj Singh Rajput

Co-founder Rich experience of leading business end to end, running a P&L, building strategic
business partnerships, driving market development, driving digital transformation.
Entrepreneurial mindset in solving business problems, identifying new opportunities and
building business with exponential growth trajectory, finding the right talent, and building
teams with a high-performance culture

18
OUR CORE VALUES

At Movidu, we believe that our values are what make us who we are. They define who we are
as individuals and how we interact with the world.

Integrity - We value honesty, transparency and trust in our relationships.

Collaborative approach- We believe that together, we can do more than we can alone.

Owning your work- We believe you should take pride in your work and respect the efforts
of others.

Not afraid to fail- We believe that failure is a natural part of growth, so we're not afraid to
try new things out and learn from them.

Desire to win- We want to be the best at what we do, and that means always striving for
excellence.

19
OUR VISION

We are India's largest platform for trained Freshers and Interns Workforce. We provide our
students with live project opportunities in various industries, including the IT sector, banking,
finance and insurance, healthcare, engineering and construction. Our mission is to be the best
place for students to find work, gain practical experience in their chosen field by working on
projects with companies before they get hired.

We believe that education should be affordable and accessible to everyone. We also believe
that education should be relevant to students' interests and needs—not just what is required
by employers. We want to enable every student who wants to learn more about something
new or gain practical experience in a particular field of interest or skill set by working with
companies on their projects before they get hired.

Our vision is to be earth's most student-centric company; to build a place where students can
come to find and discover anything they want to learn and gain practical experience in by
working with companies on their projects before they get hired.

OUR MISSION

Our core Distinction is we allow students to work with you for a period of 3 months before
you decide to hire them. And incase of an attrition, you will always have more students to
hire fromWe are assisting companies with the hiring process from the initial research and
matching stage till the final interview. We help you understand your company culture,
requirements and assessment criteria. We also provide training on skills required by your
company.

We're not just looking for anyone who wants to work hard—we want people who are ready to
go above and beyond on your project. This means they should be able to communicate
clearly, know how to work within a team dynamic, and be able to stick with a project until the
end.

20
Doing all this isn't easy—it takes training students on what skills are needed in your industry
and how they can transfer that knowledge into actionable tasks. That's why we let students
work on live project for three months before the final offer is made!

HEADQUARTERS LOCATION

1st floor, 47/B, 26th Cross, Garden Layout, Sector 3, HSR Layout, Bengaluru, Karnataka
560102, Bangalore, Karnataka, 560102 IN

COMAPY PROJECTS

21
PARTENRED COMPANIES

22
LITERATURE SURVEY

23
 LITERATURE SURVEY

Jain and Sharma, (2012) in a research article on. FMCG‘s touch every aspect of human life, it
is an integral part of a consumer dominated market and also a corner stone of the Indian
economy. FMCG‘s give ample opportunity to the marketer to give choices and comparative
advantage to the consumers as well as their own venture.

A paper by Kumar,et al., (2012) says that FMCG‘s are consumer packaged goods include
consumable items by consumers at regular intervals; these items are frequently used by the
consumers and are yielding high returns to marketers. This paper also says that preferences is
a choice between alternatives based on satisfaction and utility they provide, the study of
consumer preferences not only focuses on how and why the consumers make buying
decisions but also how and why the consumer make the choice of goods they buy and their
evaluation of these goods and FMCG‘s are based on 4 A‘s awareness, availability,
adoptability and affordability.

Gupta, Mittal, (2002), Fast Moving Consumer Goods (FMCG) sector is very important for
Indian economy. This sector touches every aspect of The Indian Fast Moving Consumer
Goods (FMCG) industry began to shape during the last fifty odd years. FMCG sector is a
cornerstone of the Indian economy. This sector touches every aspect of human life. Indian
FMCG market has been divided for a long time between the organized sector and the
unorganized sector. Unlike the US market for FMCG which is dominated by a handful of
global players, India‘s Rs. 460 billion FMCG market remains highly fragmented with roughly
half the market going to unbranded , unpackaged home made products. This presents a
tremendous opportunity for makers of branded products who can convert consumers to buy
branded products. Globally, the FMCG sector has been successful in selling products to the
lower and middle income groups, and the same is true in India.

Behura&Panda (2011). Fast Moving Consumer Goods (FMCG) can be defined as packed
goods that are consumed or sold at regular and small intervals. The prices of the FMCG are
relatively less and profits earned through such sales are more volume based. The organized
FMCG retailing in India is a new concept and is fast catching up in urban and semi-urban
Nagarajan & Khaja (2013).

Gupta&Roy, (2012) have said Marketers should try to create awareness regarding the benefits

24
of the ingredient brand and build up the confidence by delivering superior benefits of the
ingredient. Ingredient Brand should possess relevant, unique and believable benefits so that
customers will be assured that the final product will be able to fulfill their needs. Marketers
can identify an unsatisfied need or want of the customer. Then with the help of ingredient
brand can design a customized unique solution catering to this unmet need. This will in turn
boost the product sale, increase the profit margin and strengthen the product value
proposition. There is a lot of scope for Ingredient Branding in FMCG companies. For
effective implementation of this marketing technique further empirical researches should be
conducted taking in consideration the FMCG customers and marketers perspective.

Santos et al., (2012) have mentioned that Brands may function like a social currency, which
every individual uses to assess others, and which others are expected to use in their
assessments of the individual. Brands are most probably social tools.

Correia et al., (2012) have conceptualized that Brand love reinforces the trust, interest in
continuing a relationship and faith in the future of the brand in the Journal of Brand
management.

Nugroho & Wihandoyo, (2009) says that Understanding Consumer‘s Perceived Values place
important part in winning customers over a product/service and became the major motive in
choosing the problem. To develop and improve a product, companies must know what are the
factors that consumers think as important to dig up information on how they think and
perceive variables over a product before considering in purchasing it.

Manepatil, (2013) has mentioned that Change in shopping behavior in urban India over the
past few years with consumer looking for convenience. That is they want everything under
one roof and a bigger choice of products with an increase in double income, household,
people don't have much leisure in order to make the best use of their time. As malls and
supermarket offer the option of entertainment along with shopping, younger couples prefer to
shop there No of people are attracting towards retail market.

Binninger, (2007) has mentioned that from the early 1990s on, customers‘ loyalty has come
to be a key concept again associated with many others including satisfaction, commitment,
trust, identification and the relationship with or attitude toward the brand. Often viewed as a
paradigm change, this new approach rests on the overt intent to retain existing customers.
Based on the principle that it is more cost-effective to retain one‘s customers than to capture

25
new ones, and that consumer and that consumer profitability over time is conditional on
loyalty, this process must lead to an overall improvement of the quality of relationships with
customers. It is also a way of retaining the market share in an environment often glutted by a
host of competitive offerings.

Mahalingam,&Kumar,(2012) have mentioned that Consumer behavior can be defined as the

decision-making process and physical activity involved in acquiring, evaluating, using and
disposing of goods and services. This definition clearly brings out that it is not just the buying
of goods/services that receives attention in consumer behavior but, the process starts much
before the goods have been acquired or bought. Mark,(2008) is a basic principle of brand
management and of marketing more generally. This principle is as important today as it has
ever been. But consumers aren't a fixed target. Consumers change: existing consumers of a
brand develop new needs, change their preferences, alter their habits and acquire new skills
for engaging in purchasing and consumption; fresh consumers come into new and established
markets, with their own needs, preferences and skills.

Dutta, (2012) has expressed that a brand is a perceptual reality for the consumers. Consumers
draw strength from the superior value associated with the perceptual entity of the brand. The
brand perspective thus decides the fate of the firm in the market place. Brand is a powerful
force that binds the consumer with the organization. Guise, (2011) brand preference
represents another important construct in the buying process, brand preferences vary from
people to situations. Pride &Ferrell, (2009) Brand loyalty is a consumer favorable attitude
towards a specific brand, brand preference is a stronger degree of brand loyalty and a
consumer definitely prefers one brand over competitive offerings and will purchase this brand
if available.

Batra&Kazmi, (2004/2010) revealed that branding is a major decision issue in managing the
products. Well known brands have the power to command price premium, branding has
always been an important aspect in marketing, brands live in minds of consumers and are
much more than just tag for recognition and identification, they are the basis of consumer
relationship and bring consumers and marketers closer by developing a faith and trust
between them. Brands are believed to be the real generators of wealth of 21st century and
determine the market value of the business entities.

Blakeman, (2007) states that brand is a products identity and its legacy. By building strong

26
brand image for a product or service you give the product a personality, an image, and the
single voice or message for a brand. This ultimately determines how the consumer thinks
about the product or service and how it stands out from the competition. The more unique
persona you create the more memorable the brand will be. The brands distinctive look should
be one of the factors that make the product or service stand out from its competition.

Mishra et al, (2011) branding is the identification of a product that maintains an image
through the use of symbols, design or brand name. The biggest challenge for a successful
brand is to protect reputation. Building successful brands is a very challenging process. It has
also been pointed out that manufacturer‘s produce what their consumers want. They adopt
their brand packaging and labeling which may attract their consumers. All marketing the
books also highlights that activities revolve round the satisfaction of the needs and wants of
consumers.

Gaur, (2011) has pointed out that the importance of strong brands means that brand building
is an essential marketing activity. Successful brands can reap benefits in terms of premium
prices, achieving distribution more readily and sustaining high and stable sales through brand;
loyalty. Consumers tend to trust strong brands. Strong brands also benefit consumers in that
they provide quality certification which can aid decision making. A strong brand provides the
foundation for leveraging positive perceptions and goodwill from the core brand to brand
extensions. Strong brands, typically product category leaders are important to both companies
and consumer Companies benefit because strong brands add value to companies, act as a
barrier to competition, positively affect consumer perceptions of brands, improve profit and
provide a base for brand extensions. Consumers gain because strong brands act as a form of
quality and create trust.

Pringle& Field, (2009) have mentioned in their book Brand Immorality that brands do not
have to die they can be immortal if they are managed properly and that the value of brands
needs to be preserved companies need to appreciate that successful brand management is
essential for their survival, with careful management brands have the potential to be
immortal, preserving value and customer relationships.

Haridas MP, (2011) states that Only a decade ago even brand managers observed brands as
symbols and not as carriers of identity, personality and benefits, brands were considered as
producers property. The strength of brands presence in a consumers mind is defined as the

27
level of awareness, where recognition is the weakest, recall is somewhat stronger and
dominance the strongest.

Joseph&Parker, (2005) Consumers may perceive value for their feelings when in contact with
your brand, such as feeling more secure, more comfortable and more competent.

Lillien, et al, (2011) evaluation stage the consumer forms a rank set of preferences for the
alternative product in his evoked set and an intend to purchase the product he likes best. A
consumer‘s purchase decision is also influenced by situational factors as family income, total
cost of the product.

Gautam, & Jain,(2011) refer that consumer behavior involves understanding that acquisition,
consumption and disposition can occur over the time in a dynamic sequence. The manner in
which consumers buy is also extremely important to marketers.

Pradhan,(2009) ,states that a supermarket is large, low cost, low margin high volume self
service operations designed to meet the need for food and no food items controlling more
than 30%of the grocery markets in the world.

28
 METHODOLOGY

29
 METHODOLOGY

Data integration: First collected and integrated all the data from different sources Data
selection: Then selected the data that can be used for data mining

Data cleaning: Most of the time, data gathered are not clean and may contain errors, missing
values, noisy or inconsistent data. So, they have to remove. This process was done manually

Data transform: This step is done for get more efficient results and to gain results in
understandable manner. Mainly normalization was done for the data

Data mining: In this step the algorithms were used for mine the database. The prediction was
done by using Time Serious algorithm

Pattern Evaluation and Knowledge Presentation: First some of the results that are not
related were removed fine tune other results well to understand by the users of the system.
Using Time Serious algorithm can forecast most tourist attracted hotels, destinations, room
types and board basis which useful for management decisions in Patanjali companies. The
result will be predicted by representing bar charts.

FIGURE 3: PREDICTION AND ANALYSIS

30
 Figure 1. Process of creating a report on Power BI

The following defines the steps of this methodology as illustrated in the above block diagram.

1. First, collect all the databases and copy them for that first clean and transform the dataset to
make it more usable.
2. For creating reports, use filters to drill down based on product and employees.

3. Determine sales by revenue, number of units sold, individual product revenue, and revenue
generated under each supervisor.
4. Diagnose daily growth in revenue and create a drill-down table with relevant columns.

5. Incorporate an easy button for better UX.

31
 6. Publish and share the dashboard with the Power BI service.

Extract Data

The dataset for sales Analysis contains Employee data, Electronic Product data, and Sales
data. The datasets for sales prediction were obtained from GitHub.This Advertising dataset
contains 347 rows of sales records with advertising details from January 2015 to March
2019.
Transform Data
Sales Analysis database can be directly loaded but for prediction of sales, application of a
machine learning algorithm was needed. So, data can‘t be used in its normal form as the
data needs to be devised before applying it in machine learning models. Therefore, before
loading the data into Power BI it is needed to be transformed first. This method is used to
solve problems that are not yet known by the knowledge extractor. Proper formatted and
cleaned data is necessary for preprocessing.
In the advertising dataset, there was a linear relationship between all three of those channels
(T.v, Radio, and Youtube) ultimately this will be able to use in the equation i.e predicted
sales is the sum of multiple of those channels and the coefficient.
y = b0 +b1*x1 + + bn*xn
where y is the predicted sales, x1,. ,xn are the channels, and b is the coefficient.
To isolate those coefficients and to find the value of predicted sales use of linear regression
was done using python script in Power BI.
Algorithm used
Linear Regression is the most common and widely used Machine Learning algorithm. It is
used for establishing a linear relationship between the target or dependent variable and the
response or independent variables. The linear regression model is based upon the following
equation:
yb0 + b1x1 + b2x2 + b3x3 +……+ bnxn
where y is the target variable, b0 is the intercept, x1, x2, x3,….xn are independent variables,
and b1, b2, b3,…, bn are their respective coefficients.
The main aim of this algorithm is to find the best fit line between the target variable and the
independent variables of the data. It is achieved by finding the foremost optimal values for
all b. With the best fit, it is meant that the predicted value should be very close to the actual
values and have minimum error. Error is the distance between the data points to the fitted

32
regression line and generally can be calculated by using the following equation:
Error = y1 - y2
where y1 is the actual value and y2 is the predicted value.

Load Data
For the sales analysis dashboard, an Electronic product sales database was loaded in Power
BI which consisted of employee data, electronics product data, and sales data. And for the
sales prediction dashboard, after transforming the advertising database the database was
loaded in power BI which consisted of Date, T.V, Radio, and newspaper data.
Create Reports in Power BI
Using the donut chart, the revenue by the supervisor is displayed containing four
supervisors along with revenue in percentage and number as shown in figure 2. A drill-
down option is provided to get the employee- wise data. So, data can be easily drilled down
to the next level. Revenue by date is displayed using the area chart which is containing
revenue date-wise as shown fig

33
TOOLS USE

Power BI

Power BI is an analytical application for analyzing data and sharing knowledge in business.
Power BI includes cloud integration that provides data storage capabilities such as data
optimization, data availability, and interactive dashboards. Microsoft releases additional
support features called Embedded Power BI on the Azure cloud platform. Power BI also can
combine different databases, files, and web services so that it can quickly make changes or
fix data and problems automatically. Power BI also ensures the security of publishing
reports generated within the company and automatically manages the most up-to-date
information. Power BI can also integrate all data into a company, whether cloud or in-house
because Power BI has a gateway that allows you to connect to SQL Server data, analytics
service models, and many other data sources on the dashboard.

AutoML is a feature of Power BI Dataflows that enables users to create, train, and plead
machine learning models. The best part is that it is done 100% inside of Power BI. AutoML
is designed for business analysts in mind. AutoML empowers business analysts, or
traditional BI engineers, to learn the basics of machine learning, while at the same time
developing a model for making useful predictions. It currently supports the
implementation of Binary Prediction, General Classification, and Regression models.
Additional model types, such as Forecasting, and the ability to export ML models made in
Power BI to Jupyter Notebooks can be expected in the future. This can be of great help to
analysts, or developers who want to make an example of Power BI performance, but then
refer you to a data scientist to refine and set a standard model.

Spyder

It is a free and open scientific environment written in Python and designed for data
scientists, IT engineers, and data analysts. It features a mixture of the advanced editing,
analysis, debugging, and profiling functionality of a comprehensive development tool with
interactive execution, deep inspection, and pleasant visualization capabilities of a scientific
package. Spyder integrates with a variety of prominent packages within the scientific
Python stack, including NumPy, SciPy, Matplotlib, pandas, IPython, SymPy, and Cython,
also as other open- source software.

34
Microsoft Excel

It is a spreadsheet developed by Microsoft for Windows, Mac OS, Android, and iOS. It
features graphing tools, pivot tables, and a macro programming language called Visual
Basic Application. Microsoft Excel has the common features of all spreadsheets, employing
a grid of cells arranged in numbered rows and letter-named columns to arrange data
manipulations like arithmetic operations. In addition, it can display data as graphs,
histograms, and charts, with a limited three-dimensional graphical display.

Figure 2. Revenue by supervisor

Figure 3. Revenue by Date

Figure 4. Revenue by Employee name

35
Revenue by Employee name chart is shown in figure 4. Employees who are
booking the sale product. So, the largest area block is the employee who is
providing the maximum revenue. Figure 5 chart is the product-wise revenue
chart and laptop/ computer is giving the highest revenue and revenue is in
million.

Figure 5. Revenue by product name

36
Data collection: Collecting historical sales data of Patanjali from various sources such as the
company's financial statements, government reports, and industry publications.

Data cleaning and preparation: Cleaning the data by removing duplicates, correcting
errors, and preparing it for analysis using tools such as Excel and Python.

Data analysis: Analyzing the sales data using statistical tools such as regression analysis,
time-series analysis, and data visualization tools such as Power BI to identify patterns and
trends in sales performance.

Predictive modeling: Using predictive modeling techniques such as linear regression, time-
series forecasting, and machine learning algorithms to forecast Movidu Technologies Pvt.
Ltd. future sales.

Limitations: Identifying any limitations of the study, such as data availability or limitations
of the methodology, and providing recommendations for future research.

37
 RATIONALE/REASON BEHIND THE STUDY

The рurроse оf this рrоjeсt is to design а sаles dаshbоаrd fоr the sаles deраrtment
using Роwer BI tо demоnstrаte mоnthly sаles рerfоrmаnсe whiсh will рrоvide dаtа аnd user-
relаted infоrmаtiоn. The content displayed should be fully visuаlized аnd аррeаling. In
аdditiоn, аs infоrmаtiоn аre nо lоnger relevаnt tо deсisiоn-mаkers, the overall соnstruсtiоn
рrосess should be trаnsраrent within the department. The finаl dаshbоаrd саn be соnsidered
аs а сustоmized versiоn. Users can still fоllоw the design process or mоdify it if а new need
аrises. This project aims to seek ways to improve overall sales via analyzing the data and
generate sales performance dashboards for better decision making. This was done by
identifying the highest & lowest selling products while drilling down into different
dimensions to understand the hidden patterns, thus the objective is to build the most effective
predictive model with optimum accuracy and evaluation measures to predict future sales and
to draft valid analysis by evaluating the customer buying behavior to improve their future
sales.

38
 OBJECTIVES

 To analyze Movidu Technologies Pvt. Ltd. historical sales data and identify patterns
and trends in sales performance.
 To identify the key factors that influence Movidu Technologies Pvt. Ltd. sales
performance, such as consumer demographics, marketing efforts, and product
offerings.
 To use Power BI to create interactive dashboards and visualizations that provide
insights into Movidu Technologies Pvt. Ltd.sales performance and trends.
 To develop predictive models using Power BI that forecast Movidu Technologies Pvt.
Ltd.future sales based on historical data and trends.
 To provide recommendations to Movidu Technologies Pvt. Ltd.management team on
strategies to improve sales performance and capitalize on emerging trends in the
FMCG market.

39
 HYPOTHESIS

 Movidu Technologies Pvt. Ltd. Sales have been steadily increasing over the past few
years due to the rising popularity of Ayurvedic and natural products in India.
 There is a strong correlation between the marketing efforts of Patanjali and its sales
performance.
 The COVID-19 pandemic has positively impacted the sales of Patanjali due to
increased awareness of health and immunity-boosting products.
 The sales of Movidu Technologies Pvt. Ltd. FMCG products are likely to increase in
the future due to the company's expansion plans and increasing market penetration.
 Power BI can accurately predict future sales trends for Patanjali by analyzing
historical sales data, consumer demographics, and marketing trends.

40
DATA ANALYSIS & INTERPRETATION

41
 DATA ANALYSIS & INTERPRETATION

Indian FMCG Market Dynamics:

When we talk about FMCG, the first thought that lingers in our mind are products that are
consumed on a daily basis. The increasing disposal income in rural India and low penetration
level in rural market are propelling the Indian FMCG sector at an accelerating speed. The focus
on agriculture, MSMEs, education, healthcare, infrastructure and tax rebate under the Union
Budget 2019-2027 is expected to directly impact the FMCG sector. These initiatives are
expected to increase the disposable income of the common people, especially in the rural area,
which will be beneficial for the sector. The FMCG sector is a vital contributor to India‘s GDP,
being the fourth largest sector in the economy it creates employment for more than 3 Mn
people. Its main elements are household care, personal care and food and beverages. The
phenomenal growth of the FMCG industry especially in the tier II and tire III cities in India is
mostly due to the improvement in the standard of living of the people of such cities and the rise
in the level of disposable income. Over the last few years companies like Dabur, HUL and ITC
have managed to change the face of the FMCG industry in India by using cutting edge
technology in production and a very strong distribution channel. Companies like Colgate
Palmolive and Britannia have also managed to penetrate into the urban areas of the country. It
is observed that with an investment of US$254.50 Mn, Wipro is diversifying and expanding its
product range in energy drinks, detergents, and fabric conditioners. On the other hand, Patanjali
will spend US$743.72 Mn in various food parks in Maharashtra, MP, Assam, Andhra Pradesh,
and UP. It is advisable for the FMCG companies to encase opportunities like increasing
consumer income, changing consumer lifestyle, aspiring rural consumer and consistent
economic growth by utilizing its strengths.

Indian FMCG Market Segment Analysis:

The Indian FMCG Market is segmented by Product Type, Demographics, and Sales Channel.
Based on the Product Type, the market is segmented into Food & Beverages,
Pharmaceuticals, Household & Personal Care, Consumer Electronics, and Others. Food &
Beverages segment is expected to hold the largest market shares of xx% by 2027. The changing
preferences of the upward middle class families from the urban areas gave importance to food
& beverages sector and thus, fuelled the growth in the last few years. India is the world‘s

42
second largest producer of food, next only to China, and has the potential of being the largest
player in food and agricultural sector. The food processing industry is one of the largest
industries in India and is ranked fifth in terms of production, consumption, export, and expected
growth. These are the key factor that drives the growth of this segment in the Indian FMCG
market during the forecast period 2021-2027.

Based on the Demographics, the market is segmented into Urban and Rural. Rural segment is
expected to grow rapidly at a CAGR of xx% during the forecast period. Accounting for a
revenue share of around 45 %, rural segment is a large contributor to the overall revenue
generated by the FMCG sector in India. Demand for quality goods and services have been
going up in rural areas of India, on the back of improved distribution channels of manufacturing
and FMCG companies. Based on the Sales Channel, the market is segmented into Online and
Offline. Online Retail segment is expected to grow rapidly at a CAGR of xx% during the
forecast period. Online shopping has become popular in recent past. While offline sales
comprising kirana stores continues to dominate the share, being the largest sales channel for
overall FMCG retail sales, growth in sales through online shopping trend especially e-
commerce is gradually outpacing the growth of FMCG products in offline trade. Post the
announcement of demonetization and implementation of GST, the overall online trade is
expected to grow at even faster rate with e-commerce. A faster growth in internet user base,
broadband data consumption, and rise in smartphone penetration rate and in digital transaction
is expected to drive the growth. E-commerce companies like Amazon are strengthening their

43
business in FMCG sector by positioning their platform pantry as front line offering to drive
daily product sales. The growing consumer trust and confidence in online buying has helped e-
commerce platforms to expand their share in India's total FMCG retail sales by as much as
three times. These are the key drivers that boost the growth of this segment in the Indian FMCG
market during the forecast period 2021-2027.

Indian FMCG Market Regional Insights:

North India dominates the Indian FMCG market during the forecast period 2021-2027. North
India is expected to hold the largest market shares of xx% by 2027. North India FMCG market
was reported growth of 4.1% in September 2020. This factor is expected to drives the growth of
North India region in the Indian FMCG market during the forecast period 2021-2027. South
India is expected to grow rapidly at a CAGR of xx% during the forecast period. South India
FMCG market was reported growth of 1.8% in September 2020. East India is the fastest
growing region in the Indian FMCG market. East India FMCG market was reported growth of
1.3% in September 2020. The objective of the report is to present a comprehensive analysis of
the Indian FMCG Market to the stakeholders in the industry. The past and current status of the
industry with the forecasted market size and trends are presented in the report with the analysis
of complicated data in simple language. The report covers all the aspects of the industry with a
dedicated study of key players that include market leaders, followers, and new entrants.
PORTER, PESTEL analysis with the potential impact of micro-economic factors of the market

44
have been presented in the report. External as well as internal factors that are supposed to affect
the business positively or negatively have been analyzed, which will give a clear futuristic view
of the industry to the decision-makers. The reports also helps in understanding the Indian
FMCG Market dynamic, structure by analyzing the market segments and project the Indian
FMCG Market size. Clear representation of competitive analysis of key players by product,
price, financial position, product portfolio, growth strategies, and regional presence in the
Indian FMCG Market make the report investor‘s guide.

Indian FMCG Market Scope:

Global Indian FMCG Market

Report Coverage Details
Base Year: 2020 Forecast Period: 2021-2027
Historical Data: 2016 to 2020 Market Size in 2020: US $ 110 Bn.
Forecast Period 2021 to 27.9% Market Size in 2027: US $ 615.87Bn.
2027 CAGR:
Segments Covered: by Product • Food & Beverages • Pharmaceuticals •
Household & Personal Care • Consumer
Electronics • Others
by • Urban • Rural
Demographics
by Sales • Online • Offline
channel

45
Fast-moving Consumer Goods Industry

Indian FMCG landscape was fiercely competitive with the presence of reputed global and
domestic brands. The FMCG industry grew at the rate of 12 per cent with annual revenue of
US$49 billion in 2016 (IBEF Report, 2016b). The food products dominated the FMCG
category with 43 per cent, followed by personal care (22%) and fabric care (12%) (Shine
Report, 2018). Most of the growth in the Indian market was going to come from rural areas,
where penetration was significantly low. The rural FMCG industry was projected to grow by
compound annual growth rate (CAGR) of 18.1 per cent with a potential of US$100 billion
during 2015–2025 (IBEF Report, 2018). The Indian government initiatives such as National
Rural Employment Guarantee Scheme, Food Security Bill and Direct Benefit Transfer had
also increased the disposable income in rural areas. Companies were looking to increase their
foothold in Tier I and II cities with the help of expanding modern retail, which was expected
to reach US$180 billion by the year 2020.

Traditionally, the Indian FMCG (fourth largest sector in Indian economy) industry is divided
into three core segments: food and beverages (18%), healthcare products (32%), and
household and personal care products (50%) (IBEF Report, 2016a). Hair care products were
the leading segment, accounting for 23 per cent in terms of revenue. Food products were
second with 18 per cent share followed by health supplements and Oral Care products, which
had a 16 per cent market share each. Certain food products such as packaged atta (wheat
flour), biscuits and soft drinks were a billion-dollar category. The urban segment had the
largest consumer base (65%) in India with the rest (35%) being part of the rural segment.
Approximately half of the rural spending was on FMCG products. Organizations such as
HUL, Dabur and ITC had 30–45 per cent of their revenue through rural sales alone. Ghee,
shampoo and hair oil, toothpaste and herbal cosmetics were the leading sale categories of
PAL (Table 2).

46
 Table 2. Best Sellers of PAL

Sl. No. Product Category Revenue (in Million USD)* (2015–2016)

1. Ghee 107.7

2. Shampoo and hair oil 50

3. Toothpaste 46.2

4. Herbal cosmetics 38.5

Pull Marketing with Umbrella Branding

PAL used a unique mix of marketing capabilities. It adopted non-conventional ways of

launching products into the market.

Product

PAL followed three philosophies when it introduced any product in the market. These
included Swadeshi (manufactured in India) products, Ayurvedic products (Herbal) (no
chemicals, preservatives, etc.) and products with value proposition around wellness and
nutrition. This approach was entirely different as compared to competitive brands. PAL
leveraged this philosophy to win the trust of customers. Baba Ramdev highlighting the all-
Swadeshi philosophy mentioned:

Unlike big business groups, my advertising work is handled by Vermillion, an Indian

advertising agency. (Ohri, 2016a)

In all its advertisements, PAL consistently highlighted its herbal (non-chemical) content. PAL
claimed that the company‘s products were superior in terms of wellness aspects compared to
all other similar products available in the market from competing brands.

47
Packaging

PAL had invested in modernizing the processes of quality control and packaging. The product
packaging had a barcode and a hologram similar to the products of its close competitors.
However, it ensured that the packages looked simple. It went well with their core philosophy
of simplicity. Looking at the growth of PAL and its related packaging requirements, the top
packaging companies like Manjushree Technopack had set up a packaging plant in Haridwar,
the base location of PAL (Chatterjee, 2016).

Pricing

PAL claimed that its sole objective was to make quality products and make them available to
the masses at a reasonable price. Most of the products barring Ghee and hair oil were priced
10–30 per cent cheaper than the closest competitor product. However, in certain categories
due to increase in raw material cost and a need for higher margin, PAL increased the prices.
The price of a 100 g tube toothpaste has gone up from ₹28 to ₹40, similarly for anti-
dandruff shampoo prices had gone up from ₹85 to ₹95. Nonetheless, products were still
cheaper as compared to close competitors even after this increase (see Table 3). The price
differential itself acted as a strong reason to attract additional consumers, especially from the
lower income group to opt for its products, thereby increasing sales.

Table 3. Pricing at PAL (In INR)

Sl. Product Quantity PAL Price HUL/P&G/ Difference

No. (with Source Link) ITC/Dabur/Himalaya in Price
Price (with Source Link) (%)

1. Honey 1 kg 260 380 46

(goo.gl/sM0BCH) (https://goo.gl/654dAU)

2. Anti-dandruff 200 ml 110 129 17

shampoo (https://goo.gl/c0i67G) (https://goo.gl/TYbUcu)

3. Toothpaste 150 g 75 101 35

(https://goo.gl/rtsWbc) (https://goo.gl/L2DN1r)

4. Bathing soap 75 g 13 30 131

(https://goo.gl/tHNXsI) (https://goo.gl/Up89U8)

5. Detergent 250 g 16 25 56
soap (https://goo.gl/px28Og) (https://goo.gl/sjkebC)

6. Biscuit 75 g 10 25 150

48
 (https://goo.gl/Bt2MF0) (https://goo.gl/GmX0FE)

7. Noodles 70 g 15 40 167
(https://goo.gl/AaI1VT) (https://goo.gl/ieHbzJ)

8. Amla juice 1L 100 200 100

(https://goo.gl/3tlXZB) (https://goo.gl/8Qp8Cx)

9. Hair oil 210 ml 65 56* 14

(https://goo.gl/dpSVom) (https://goo.gl/9p2wyY)

10. Cow ghee 1L 560 482 14

(https://goo.gl/WhroXq) (https://goo.gl/Sp1CjA)

Promotion

FMCG companies formulated different branding strategies for different demographic regions.
PAL followed mass marketing approach. It sold all its products under one umbrella brand of
‗Patanjali‘. Every product, whether a shampoo or an incense stick, carried the same brand.
Traditionally, umbrella (single) brand was not preferred by organizations as target customers
were spread across various demographics, and branding issues (if any) in one product line
would have affected other product lines. Many companies, therefore, considered umbrella
branding a risky proposition.

The company invested a substantial portion of profit for charitable causes (Zarabi, 2015).
PAL had opened ‗University of Patanjali‘ with a motto to reduce illiteracy and poverty in the
country. PAL relied heavily on word of mouth. Baba Ramdev demonstrated products to a
large audience during his Yoga sessions. Any coverage to Baba Ramdev or Acharya
Balkrishna in the media added to the promotion of ‗Patanjali‘ as a brand in the minds of the
current and prospective customers. This model had worked well for PAL as has been
reflected in sales revenue growth over the years (see Figure 1).

PAL usually advertised multiple brands in a single advertisement (see Figure 3 and Figure 4).
This was in contrast to the FMCG industry trend where the company product advertisement
focussed on a single product only. PAL advertisement had captions like ‗Don‘t risk the lives
of your loved ones and innocent kids by compromising on purity. Adopt 100 per cent pure
and 100 per cent world class quality Patanjali products only‘. (The Times of India, 2017)

49
Revenue of Patanjali India from financial year 2010 to 2021

In the financial year 2022, the revenue amounted to about 99 billion Indian rupees. The
revenue showed an increasing trend in the company since financial year 2010.

50
User Stories:-

The demand overview and user stories helped me determine my data

requirements and followed up on the data availability from the client. Jen
provided us with data from their CRM system and we were able to collect the
initial data.

Having understood my data sources and the formats in which the data was
stored, I settled on SQL for querying the relational data.

51
Data Cleaning and Preparation Using SQL- Date Table

For my time series operations, I needed a date table and therefore cleansed the
Dim_Date Table.

I then proceeded to the data preparation phase which entailed cleaning the data
while referring to the business request and demand overview. At this point I
selected the Fact and Dimension tables to be used in the analysis based on the
request and user stories.

52
Data Cleaning and Preparation Using SQL- Customer Table

Data Cleaning and Preparation Using SQL- Product Table

53
Data Cleaning and Preparation using SQL- Sales Territory Table

Data Cleaning and Preparation with SQL- Internet Sales Fact Table

Once I had the tables needed for the analysis I loaded the data into Power BI for
data modeling. I created the relationships between the tables as necessary using
the primary and foreign keys to make filtering the results effective.

54
Data Model

In the report view of Power BI I performed the necessary calculations using

DAX measures for the analysis. I then created dashboards based on the demand
overview and user stories after which I published the visuals to Power BI Service
for sharing with the stakeholders.

I first prepared a Sales Overview.

55
Sales Overview Dashboard

The Sales Manager wanted a dashboard overview of internet sales that would
give details on sales and the products customers liked most. She also wanted to
compare sales over time against budget to know if they met targets or not.

I then prepared a Customers Overview dashboard to help the Sales

Representatives know their customers better. This dashboard details customer
sales by gender and makes it possible for the sales team to know which products
best appeal to men or women. It also shows the total sales from the top
customers enabling sales representatives to either upsell their products or make
necessary follow up to retain these customers.

56
Customers Overview Dashboard

Finally, I prepared Products Overview to give the team insight into the products
that are ordered most, the ones that bring in the most sales and the regions from
which most orders are made.

57
 Figure 6. Sales Analysis Dashboard
In this Dashboard, the total revenue, the number of units sold, Revenue by date using area
chart, Revenue by product name using a clustered bar chart, and also, we have used a treemap
to display revenue by employee name and donut chart to display revenue by the supervisor is
displayed. On the header, the use of cards is done to select attributes and a next button to
navigate to the next dashboard.

Sales Prediction

Figure 7. Sales Prediction Dashboard

This sales prediction model is made using multiple linear regression in python and is
visualized into an interactive dashboard using power bi and advertising dataset. In this
dashboard, users have to enter the investment inputs of T. V, Radio, and YouTube advertising
and it predicts the expected sales. In addition to that, one Q&A section is added where users
can ask any question regarding the data.

58
CONCLUSION

59
 CONCLUSION

 The construction of business intelligence dashboards can be used as a reference in

decision-making processes.
 The data cleaning process is the most important stage of producing the right information.

 User involvement from process and design in result verification will greatly improve
the quality of the required dashboard.

 According to this case study, the recommendations for continuous improvement are:

 The pre-built database needs to be upgraded to make it function effectively and

efficiently to effectively support information needs in many companies owned by the
company.
 Advanced dashboard upgrades will also be done for business components such as
financing, hiring, manufacturing, and other businesses.
 It uses Power BI at a higher level (guessing and interpretation) by the machine learning
should be done at a level of advanced development so that it can cover sophisticated
modeling and data integration conditions and ultimately empower organizations that
make data-based decisions on all aspects of a business.
 Sales analytics via a consistent interpretation offers a wide range of actionable
knowledge to businesses where it brings a competitive edge. This actionable knowledge
needs more support from predictive analytics to formulate solid business strategies to
win the current competitive business environment.
 Predictive analytics allows businesses to foresee future events to effectively implement
the formulated/designed action plans to enjoy competitive advantages and gain more
profits.
 The sales analytics revealed lots of useful insights on the sales performance, market
basket analysis, and customer analysis which enlighten ways to understand the current
situation.
 The predictive models are evaluated and compared using the measures such as accuracy
to get the best fit model. In the evaluation process, the multiple linear regression model
has been identified as the best-fit model for this problem with different channels.

60
Sales Overview

1. The total sales amount from internet sales was 29,312,291 against a budgeted revenue
of 21,100,000. This depicted a positive variance of 38.92% which shows that overall
the business met it‘s revenue targets in the past 3 years. A quick filter on months
shows the months in which revenue targets were not met and their variances.

2. On total sales per product category, Bikes brought in the most sales at 28,272,853. The
best selling product was the Mountain-200 Black, 46 with sales totaling 1,373,454 .
Accessories were second with total sales amounting to 700,014. Total Clothing sales
were 339,424.

3. Lynn Tsoflias was the best performing employee in terms of sales with her total sales
amounting to 9,039,228. The 3 worst performing employees in terms of sales were
Tsvi Reiter at 12,238, Michael Blythe at 6,532 and Jillian Carson at 2,998.

Customers Overview

1. Total Customers were 18,484. Total number of Orders were 60,384. This shows a
likelihood that most customers were repeat clients and new clients were few.

2. The insight on top customers going by the total sales gives the company an opportunity
to apply ‗KYC‘ better. Knowing the top customers‘ product likes and preferences will
help the sales team to tailor products to their needs.

3. The top 5 customer cities with the highest sales were London 802,730, Paris 539,675,
Wollongong 335,306, Warnambool 327,007 and Bendigo 314,537. This shows the
location of the clients who made the most overall purchases allowing the sales team to
drive sales and marketing efforts in these regions to retain existing customers and
attract new ones.

4. On gender analysis, the customers were 50.59 % female with sales totaling 14,791,170
and 49.41% male with sales amounting to 14,521,121. The top cities with women
customers were London, Paris, Brisbane, Wollongong and Caloundra. The cities with
the highest male customers were London, Paris, Sunbury, Warnambool, and Burbank.
The company exhibited highest sales in London and Paris which are also favorites for
both female and male customers.

61
 5. Despite having the most orders, accessories (36,092) was not the best product category
in total sales. Bikes (15,191) brought in the most sales and this can be attributed to the
unit prices of the products.

Products Overview

1. The region with the highest product orders was Australia (13,339) followed by
Southwest(12,261). The regions with the least orders were Southeast(39) and
Northeast (27).

2. Water bottle — 30 oz., Patch kit/8 patches, and Mountain Tire Tube were the products
that customers ordered most. The company should increase their warehousing
operations and stock controls in Australia, Southwest, Northwest and Canada to ensure
availability of these products at all times.

3. Bikes were the best selling product category with the top 5 sub-categories being Road
bikes, Mountain Bikes, Touring Bikes, Tires and Tubes and Helmets.

62
SUGGESTION

63
 SUGGESTION

 For future work, the predictive power of reviews to predict customer behavior and
utilize it for improving the company‘s business can be implemented. Also different
algorithms like ARSA can be applied on the current dataset and their accuracy in
forecasting can be calculated.

 This framework can be applied to huge databases where the accessible memory space is
significant and must be upgraded. You can change it further to improve execution and
proficiency.

 It very well may be applied to the securities exchange, the assortment of budgetary
insights, climate conjecture and different applications that concentrate live data on an
every day and opportune premise. It works, so you can transform it as indicated by your
prerequisites.

 Explore marketing strategies that will help target and bring in new clients.

 Organize product, customer and sales training for employees especially the
underperformers to help them increase their skills which will translate to increased
selling opportunities.

 The company should utilize customer and product information for marketing strategies
that will help in retaining top customers.

 Seek to find out what makes London and Paris favorite cities for customers and employ
the same strategies in other customer cities.

 Cycling appears to be the favorite activity for people in the company‘s sales regions as
shown by the orders and total sales of bikes. The company should optimize sales by
providing more cycling products and tailoring their marketing campaigns towards this
niche market .

64
BIBLIOGRAPHY

65
 BIBLIOGRAPHY

 Beltran Borja Fiz Pontiveros, ―Opinion Mining from Large Corpora of Natural
Language Reviews‖, September 2012.
 Richa Sharma, Shweta Nigam and Rekha Jain, ―Opinion Mining Of Movie Reviews
At Document Level‖, International Journal on Information Theory (IJIT), Vol.3,
No.3, July 2014.
 A. Nisha Jebaseeli and E. Kirubakaran, ―A Survey on Sentiment Analysis of
(Product) Reviews‖, International Journal of Computer Applications (0975 – 888)
Volume 47– No.11, June 2012.
 Gautami Tripathi and Naganna S, ―Opinion Mining: A Review‖, International
Journal of Information & Computation Technology, ISSN 0974-2239, Volume 4,
Number 16 2014, pp. 1625-1635, 2014.
 Gurudeo Anand Tularam, Tareq Saeed, ―Oil-Price Forecasting Based on Various
Univariate Time-Series Models‖, 18 May 2016.
 Prajakta S. Kalekar, ―Time series Forecasting using Holt-Winters Exponential
Smoothing‖, December 6, 2004.
 Rui Yao and Jianhua Chen, ―Predicting Movie Sales Revenue using Online
Reviews‖, IEEE International Conference on Granular Computing (GrC), 2013.
 Samaneh Beheshti-Kashia, Hamid Reza Karimic, Klaus-Dieter Thoben, Michael
Lütjen and Michael Teucke, ―A survey on retail sales forecasting and prediction in
fashion markets‖, Systems Science & Control Engineering: An Open Access Journal,
Vol. 3, December 2014.

66