Академический Документы
Профессиональный Документы
Культура Документы
Purushottam Tiwari
1828469
1|P ag e
Purushottam Tiwari, 1828469
2|P ag e
Purushottam Tiwari, 1828469
Declaration Sheet
Presented in partial fulfilment of the assessment requirements for the above award. This work
or any part thereof has not previously been presented in any form to the University or to any
other institutional body whether for assessment of for other purposes. Save for any express
acknowledgements, references and/or bibliographies cited in the work. I confirm that the
intellectual contents of the work are the result of my own efforts and of no other person. It is
acknowledged that the author of any project work shall own the copyright. However, by
submitting such copyright work for assessment, the author grants the University a perpetual
royalty-free license to do all or any of those things referred to in section 16(i) of the Copyright
Designs and Patents Act 1988. (viz: to copy work; to issue copies to the public; to perform or
show or play the work in public; to broadcast the work or to make an adaptation of the work).
3|P ag e
Purushottam Tiwari, 1828469
Abstract:
Food Prediction System is simply predicting the sales in a restaurant/cafe for the
next day/week or even months by collecting the historical data from the restaurant or café. Food
Prediction System is therefore important to the sales predicting because of the large amount of
food are being wasted or even most of the restaurant food are being shortage due to the flow of
customer in restaurants. The report and project were accomplished with answering the academics
questions in mind. The whole motivation behind the project was to increase understanding on
Food Prediction and connect the dots between Food Prediction, data management, computing
and machine learning.
Acknowledgement:
First, I admire my special thanks to my project supervisor Mr. Jnaneshwar Bohara for reviewing
my project draft time to time and giving me support and direction. Likewise, I would like to indicate
my reader Mr. Rupak Koirala as well for supporting me to write this report.
4|P ag e
Purushottam Tiwari, 1828469
Contents
Abstract: 4
Acknowledgement: 4
1. Introduction 10
1.1. Historical Perceptive: 10
1.2. Current Scenario: 10
1.2.1. General Introduction: 10
1.2.2. Overall Introduction 11
1.3. Problem Statement: 11
1.4. Aims and Objective 12
1.4.1. Aims: 12
1.4.2. Objective: 12
1.5. Structure of the Report: 12
2. Literature Review (Background): 14
2.1. Emergence of AI: 14
2.2. Machine Learning (ML) and its emergence: 14
2.3. Artificial Neural Network: 15
2.4. Linear Regression: 17
2.5. Support Vector Machine: 18
2.6. Decision Tree: 19
2.7. Past Project: 20
2.8. Similar System and Function: 20
3. Development 22
3.1. Overview 22
3.2. Inception: 23
3.3. Requirement analysis: 23
3.4. Architecture and Design 23
3.5. Development: 23
3.6. Testing and Maintenance: 23
3.7. Why Agile? 24
3.8. Consideration of Frameworks for Web Application 25
5|P ag e
Purushottam Tiwari, 1828469
6|P ag e
Purushottam Tiwari, 1828469
7|P ag e
Purushottam Tiwari, 1828469
8|P ag e
Purushottam Tiwari, 1828469
9|P ag e
Purushottam Tiwari, 1828469
1. Introduction
1.1. Historical Perceptive:
In early 1970’s, Food security crisis broke out from the first time in the world, and
then the question about the food crisis is the question has become the object of the world
(School of Economics and Management, 2010). With the rapid growth of the population
the issue of the food security has become today’s problem. The rapid growth of economy
and society the food safety issue is increasingly becoming the focus of the attention in
the public. (Fu Ying, 2013). Nowadays the university’s cafeteria is not only the choice for
the student to have a lunch or dinner or breakfast. A lot of people will take online takeaway
into consideration when they are at the time of eating. So, most of the restaurants must
manage the food not to shortage of the food or the wastage of the food. (Xinliang Liu,
2016).
10 | P a g e
Purushottam Tiwari, 1828469
know the total sales of the day. The food volatile and affected by the many factors some
of them are difficult to measure and change in climate is also one of the major factors for
the food and some different from statistical coverage (School of Economics and
Management, 2010). With the help of Artificial Neural Network (ANN), food prediction
system going to predict the sales of food that are required for the food with the flow of
customer every day. An Artificial Neural Network (ANN) is a data processing paradigm
that is stimulated by the way biological nervous systems, such as the brain, procedure
information. The key factor of this paradigm is the novel structure of the data processing
system. It is composed of a large quantity of highly interconnected processing factors
(neurons) working in unison to solve specific problems. ANNs, like people, examine via
example. As a type of artificial intelligence (AI), neural network uses algorithms to make
computer systems learn besides being explicitly programmed.
11 | P a g e
Purushottam Tiwari, 1828469
ii. There is need of large amount of data where there is less data where the
data were in bill and must collect them all and put that data in excel book
and convert it into Comma Separated Value (CSV) file.
1.4.1. Aims:
1.4.2. Objective:
a. Collecting historical data from the restaurants
b. Implementing Artificial Neural Network and hybrid algorithm.
c. Train the data using the algorithm.
d. Test the data after using algorithm is working or not.
e. Understanding how the output is accurate.
f. Use the output to determine the sales prediction in a restaurant.
12 | P a g e
Purushottam Tiwari, 1828469
13 | P a g e
Purushottam Tiwari, 1828469
14 | P a g e
Purushottam Tiwari, 1828469
data is feed to the machine. (Alex Smola, 2008). For example: Long wait time for the tables in
restaurants can turn customers away or even can create hate towards the restaurants. Most of
the customers turn away due to no food or shortage of the food in a restaurant and turn to loss
by losing customer. Food Prediction System give a proper solution to the problem by predicting
tomorrow food or even next months food which make customer stable in restaurant. Prediction is
one part of machine learning and it has been in different fields like food, recommending doctors,
recommending products, table reservation, auto driving, auto booking and soon. (Rarh, et al.,
2017).
15 | P a g e
Purushottam Tiwari, 1828469
X1…xn are the given inputs to the neurons and a bias is also added to the neuron along with
inputs. W 1j…W nj are weight of the given inputs. The product of weight and input gives the strength
of the signal and a neuron receives multiple inputs from different sources and has a single output.
There is various activation function used and the most commonly used activation function is
sigmoid function:
Sigmoid Function:
1
F(x) = 1+𝑒 −𝑠𝑢𝑚
16 | P a g e
Purushottam Tiwari, 1828469
The other functions that are used are step function, Linear function, Ramp Function, Hyperbolic
tangent function, Relu Function, Leaky relu function. Hyperbolic tangent (tanh) is similar in shape
to sigmoid function but its limits are from -1 to +1 unlike sigmoid function is from 0 to 1.
17 | P a g e
Purushottam Tiwari, 1828469
into the strength of the relationship. These two techniques are used to analyze relationship
between constant variables, whereas the x2 test is an example of a test suggestion between
definite variables. Constant variables, such as day, months and year have no gaps on the
measurement scale. In contrast, categorical variables, such as food sales, have gaps on
their possible values. These two types of variables and the hypothesis about their
measurement scale were studied and distinguished. (Zou, et al., 2003).
All three expectations on which the classic statistical example relied turned out to be unsuitable
for many modern real-life problems because of the following facts:
a. The curse of dimensionality is the modern problems with high-dimensional, and if the
fundamental mapping is not very level the linear example needs an exponentially
18 | P a g e
Purushottam Tiwari, 1828469
increasing number of terms with a growing dimensionality of the input space X number
of terms with an increasing dimensionality of the input space X.
b. The fundamental real-life data generation laws may classically be very far from the
usual distribution and a model builder must consider this change to construct an
effective learning algorithm.
c. From the first two points it follows that the maximum likelihood estimator should be
replaced by a new induction example that is uniformly better, to model non-Gaussian
distributions.
19 | P a g e
Purushottam Tiwari, 1828469
20 | P a g e
Purushottam Tiwari, 1828469
Eat is another restaurant management system available for the users, which is
also online restaurant POS system where it is a comprehensive system designed
for a restaurant for a better execution of all the operations. One central place to
automatically store and manage all reservation.
21 | P a g e
Purushottam Tiwari, 1828469
• Payroll management,
• Point of Sale (POS)
• Reservation Management and
• Soon.
3. Development
The methodology used for making the ecommerce website with machine learning
is agile method.
3.1. Overview
Agile model is a combination of iterative and incremental method models with a
focus on method adaptability and consumer satisfaction by rapid delivery of working
software product.
22 | P a g e
Purushottam Tiwari, 1828469
3.2. Inception:
When the project is identified, work with stakeholder to determine the
requirement. User flow diagram, class diagram, UML diagram, etc. to demonstrate how the
feature of the system should function how it will fit in existing system. (Lucidchart, 2017)
3.5. Development:
When the requirement of the project is finish then development phase take
place when designing the prototype of the system is finish. Development phase is occurred and
system is developed according to the stakeholder feedback. UI is developed in designing and
architecture phase. (Lucidchart, 2017)
23 | P a g e
Purushottam Tiwari, 1828469
● Stakeholder Engagement:
Agile presents more than one opportunity for stakeholder and team engagement – before,
during, and after each Sprint. By involving the customer in every step of the project, there
is a high degree of collaboration between the customer and project team, providing extra
opportunities for the group to truly understand the client’s vision. Bringing working software
early and regularly increases stakeholders’ trust in the team’s capability to deliver high
quality working software and inspires them to be more deeply engaged in the project.
● Transparency:
An Agile method provides a special opportunity for customers to be involved throughout
the project, from prioritizing features to iteration planning and review sessions to frequent
software build containing new features. However, this also needs customers to appreciate
that they are seeing a work in development in exchange for this added benefit of
transparency.
24 | P a g e
Purushottam Tiwari, 1828469
25 | P a g e
Purushottam Tiwari, 1828469
In the above figure, there is a different type of client who is using a different PC and is browsing
through the browser. The user is using the web-based system through the browser. When he/she
request certain things on the system, then at first it hits the web server with the help of internet
and again with the help of internet web server hit the request of the client to the database server
then after database server looks the request of the client into the database. After getting the things
requested by the client in the database, database server send it to the web server through internet
and web server send to the system used by the user through internet. This way a user gets his
desired result set through web. (Newman, et al., 2018).
▪ PHP:
26 | P a g e
Purushottam Tiwari, 1828469
27 | P a g e
Purushottam Tiwari, 1828469
▪ jQuery:
jQuery is a lightweight, “write less, do more”, JavaScript library. The
purpose of jQuery is to make it much easier to use JavaScript on a
website or web application. jQuery takes a lot of common tasks that
require many lines of JavaScript code to accomplish and wraps
them into methods that can call with a single line of code. jQuery
also simplifies a lot of the complicated thigs from JavaScript, like
AJAX calls and DOM manipulation. The jQuery library contains the
following features:
o HTML/DOM manipulation
o CSS manipulation
o HTML event methods
o Effects and animations
o AJAX
o Utilities
▪ Laravel:
Laravel is an open source PHP framework, which is robust and
easy to understand. It follows a model view controller design
pattern. Laravel reuses the existing components of different
frameworks which helps in creating a web application. The web
application thus designed is more structured and pragmatic.
Laravel offers a rich set of functionalities which incorporates the
basic features of PHP frameworks like CodeIgniter, Yii and other
programming languages like Ruby on Rails. Laravel has a very rich
set of features which will boost the speed of web development. The
advantages of using Laravel are:
o The web application becomes more scalable, owing to the
Laravel framework.
o Considerable time is saved in designing the web
application, since Laravel reuses the components from
another framework in developing web application.
28 | P a g e
Purushottam Tiwari, 1828469
▪ Flask:
Flask is a web framework. This means flask provides with tools,
libraries and technologies that allow to build a web application. This
web application can be some web pages, a blog, a wiki or go as big
as a web-based calendar application or a commercial website.
Flask is a part of the categories of the micro framework. Micro
framework is normally framework with little to no dependencies to
external libraries. This has pros and cons. Pros would be that the
framework is light, there are little dependency to update and watch
for security bugs, cons is that some time it will have to do more work
by self or increase the list of dependencies by adding plugins. In the
case of Flask, its dependencies are:
o Werkzeug a WSGI utility library
o Jinja2 which is its template engine.
▪ Pandas:
Pandas Data Frame is two-dimensional size mutable, potentially
heterogeneous tabular data structure with labeled axes (rows and
columns). A Data frame is a two-dimensional data structure, i.e.,
data is aligned in a tabular fashion in rows and columns. Pandas
29 | P a g e
Purushottam Tiwari, 1828469
In the real world, Pandas Data frame will be created by loading the
datasets from existing storage, storage can be SQL database, CSV
file, and excel file. Pandas data frame can be created from the lists,
dictionary, and from a list of dictionary and soon.
▪ Sci-kit learn:
Sci-kit learn is a library in Python that provides many
unsupervised and supervised learning algorithms. It’s built
upon some of the technology that might already be familiar
with, like NumPy, pandas, and Matplotlib. The functionality
that sci-kit learn provides include:
o Regression, including Linear and Logistic
Regression
o Classification, including K-Nearest Neighbors
o Clustering, including K-means and K-Means++
o Model Selection
o Preprocessing, including Min-Max Normalization.
▪ Matplotlib:
Matplotlib is a python library used to create multi-dimensional
graphs and plots by using python scripts. It has a module named
pyplot which makes things easy for plotting by providing feature to
control line styles, font properties, formatting axes and soon. It
supports a very wide variety of graphs and plots namely –
30 | P a g e
Purushottam Tiwari, 1828469
31 | P a g e
Purushottam Tiwari, 1828469
4. System Requirement:
4.1. Hardware Requirement:
ROM = 40 GB or higher
32 | P a g e
Purushottam Tiwari, 1828469
33 | P a g e
Purushottam Tiwari, 1828469
Figure 4: Data
The data was collected from near Restaurant who provide me only in bill format
and must convert it into excel shown above and convert into Comma Separated
Value (CSV).
34 | P a g e
Purushottam Tiwari, 1828469
To make model fit, date column was removed as it contains date format which is not supported
by the train and test model. Date column was spilt into day, years and months which helps data
to predict the sales of the day. The data was rough and hard to understand whereas some of the
item was not clear enough to make it as the way it was. The data was taken from 2018 and the
rest of the data are just random number and the number was generated in excel by using excel
function. The date format MM/DD/YYYY which has to separate in three rows. The rows which
was separated was months, day and year which support the test and train model and helps to
predict the data.
The shape of the data is 1400 by 24 which means that it denotes 1400 row and 24 column in
whole data. We have total of 1400 data and a column of 24 and we have to separate date column
into 3 column and drop or remove the date column which means we have 26 columns in total to
predict the data.
35 | P a g e
Purushottam Tiwari, 1828469
The column of the data are shown in the figure 6. This are the column which contains the data to
predict.
36 | P a g e
Purushottam Tiwari, 1828469
The data types of the data are shown in the figure 7 where the data types of date is object which
is not supported in train and test model.
The sum of the null values in the data and there is no null values at all each and every row of the
data contains the data.
37 | P a g e
Purushottam Tiwari, 1828469
Splitting the date into year, month and day which will support to train and test the model.
Figure 10:correlation
The correlation between the data. The correlation of the data is 26 by 26.
38 | P a g e
Purushottam Tiwari, 1828469
model is a result of running the model on the testing set when training is
complete.
6.1. Overview:
During the project, Restaurant Management System build to helps
restaurant to keep the record and helps to know the inventory in the
restaurant. The Restaurant Management System is responsible to handle
to keep the record of day to day sales of food in a restaurant. It also helps
to handle to keep the record of item and also manages the table in a
restaurant. Restaurant Management also keeps the record for future
calculation to help to know about profit and loss of a restaurant. Restaurant
Management System is like SaaS system which helps user to access
through internet. SaaS (System as a Service) is a system delivery model
which a third-party benefactor hosts application and make them accessible
to customer through internet. SaaS (System as a Service) is one of the
three categories in cloud architect. (TechTarget, 2019).
Restaurant Management gives the security like log in into the page and if
the user is new then user can register to the Restaurant Management.
Restaurant Management contain dashboard, table management, daily food
consumption, order management, item management and soon.
39 | P a g e
Purushottam Tiwari, 1828469
Figure 11:Login
First page of the Restaurant Management System where the user can login to the Restaurant
Management System if the user is assigned and can get the access to use the restaurant login.
40 | P a g e
Purushottam Tiwari, 1828469
6.3. Register:
In this section, if the user has not assigned then user can assign by themselves or admin can add
them and user can access through login to the page and access Restaurant Management
System.
41 | P a g e
Purushottam Tiwari, 1828469
The database of the Restaurant Management System where all the record of the management
system is recorded here for the future references. It helps to know about the how many users are
using and how many staffs are there and what kind of order are ordered by customer.
42 | P a g e
Purushottam Tiwari, 1828469
43 | P a g e
Purushottam Tiwari, 1828469
6.5. Dashboard:
Figure 15:Dashboard
First user register if he/she has not register and login the figure 15 shows the first page after login.
Dashboard has a dummy chart and dummy value and can be replace by real time value.
44 | P a g e
Purushottam Tiwari, 1828469
Table Management is the management when order is ordered then which table contain the order
is managed. In this section, table number are added how many table are there in a restaurant and
how many table are available is known in a restaurant.
Adding table where table number and number of customers will be added. How many customers
can be fitted in a table.
45 | P a g e
Purushottam Tiwari, 1828469
In this section, category like burger, Pizza, Sandwich and soon can be added in which each
category carries sub category like: veg., buff, chicken and soon. The system user has to add
category and only they can add sub category.
46 | P a g e
Purushottam Tiwari, 1828469
Category has to add to know how much category there in restaurant management are. The index
shows that in what time it was add and also it contains date. It was timestamp which helps to
know about the which time it was added.
47 | P a g e
Purushottam Tiwari, 1828469
In this section, sub category is added to know about what kind of item is contain is a restaurant.
The items like: veg., buff, chicken, special, and other can be added with the help of category.
Category must be added first to add item. Without category item cannot be added because it is
sub category of the category item.
48 | P a g e
Purushottam Tiwari, 1828469
49 | P a g e
Purushottam Tiwari, 1828469
Artificial Neural Network should be used to predict the system and know about the prediction
accuracy. Not only using Artificial Neural Network, using other library like: Gaussian Bayes,
Random Forest classifier, Linear Regression and Support Vector Machine to know about the
prediction rate and which library is best to use to predict this kind of dataset in future. The
secondary question was what accuracy can Artificial Neural Network will give if it is used to predict
Food Prediction System? To answer secondary question, yes it has predicted Food Prediction
System with the accuracy was around 84 percent. However, the objective of this project is to
implement Artificial Neural Network and not only using Artificial Neural Network, using another
Machine Learning algorithm and compare the outcome with Artificial Neural Network.
Based on study of findings about the machine learning approach that linear regression seems
more useful for Food Prediction System, but it is not efficient for future because it does not give
much accuracy. According to study, Artificial Neural Network and Support Vector Machine are the
best algorithm to use for any other dataset and the accuracy of this project is quiet much higher
than other algorithm. For the future reference, Artificial Neural Network and Support Vector
Machine has the best accuracy and it also give the best predicted value.
11. Testing:
Testing is finding out how well software is working. Testing is also defined
as the activity to patterned whether the definite results match the predictable results and to confirm
that the software system is defect free. It includes implementation of a software module or system
module to assess one or more properties of interest.
50 | P a g e
Purushottam Tiwari, 1828469
• Test Plan
Test case Objectives
1 User should login to the page
2 User should register to the page
3 User should add
4 User should edit
5 Using prediction ANN
6 Using SVM Prediction
• Test Result
51 | P a g e
Purushottam Tiwari, 1828469
52 | P a g e
Purushottam Tiwari, 1828469
53 | P a g e
Purushottam Tiwari, 1828469
54 | P a g e
Purushottam Tiwari, 1828469
55 | P a g e
Purushottam Tiwari, 1828469
56 | P a g e
Purushottam Tiwari, 1828469
12. Conclusion:
12.1. Overall Conclusion
At last, this project was building to predict the sales of food in a restaurant
using different machine learning approaches. This project, Food Prediction System is built and
under many circumstances it also has to compare different machine learning approaches. This
project presented a food prediction system prediction accuracy comparison between different
57 | P a g e
Purushottam Tiwari, 1828469
machine learning algorithms such as Artificial Neural Network, Linear Regression, Support Vector
Machine, Gaussian Bayes, Random Forest and Decision Tree. Overall, Support vector Machine
and Artificial Neural Network performed well than other classifier but when done the classification
prediction while Decision Tree preformed other while performing the regression analysis.
The Restaurant Management is another solution for a restaurant and which is suitable for
restaurant. Restaurant Management System helps to keep record of food item and help to
generate profit in future. However, there is normal prediction integrate into Restaurant
Management System where it can be extended and allow end user to write their own prediction
engine and execute it.
However, the software development life cycle has designated that the selected methodology has
been followed. Choosing methodology and the development life cycle was hard to follow.
Evaluating the project by clearly explaining functional and non-functional requirement and testing
of the project has been fulfilled.
Restaurant Management System helps to calculate profit or loss in the end of the day which
means that restaurant has not to bother about calculating profit or loss which saves restaurant
time. Restaurant Management System has different data record system like how many staff are
working and how many customers can fit in one table or how many customers are fitted in a whole
table. Even Restaurant Management System also helps to determine the lack of food in order to
maintain restaurant.
58 | P a g e
Purushottam Tiwari, 1828469
References
Alex Smola, S. V., 2008. Introduction to Machine Learning, Cambridge: Cambridge University
Press.
Fu Ying, L. F., 2013. Application of Internet of Things to the Monitoring System for Food Quality
Safety. Application of Internet of Things to the Monitoring System for Food Quality Safety, p. 296.
Honghong, L., 2010. A prediction and influence factor analysis of China's food production. A
prediction and influence factor analysis of China's food production , pp. 30-33.
Kapi, Mittai, Khanduja, D. & Tewari, P. C., 2018. An Insight into "Decision Tree Analysis". An
Insight into "Decision Tree Analysis", 4.25(111-115), p. 111.
Lucidchart, 2017. The Stages of the Agile Software Development Life Cycle. [Online]
Available at: https://www.lucidchart.com/blog/agile-software-development-life-cycle
Marr, B., 2018. What Are Artificial Neural Networks - A Simple Explanation For Absolutely Anyone.
[Online]
Available at: https://www.forbes.com/sites/bernardmarr/2018/09/24/what-are-artificial-neural-
networks-a-simple-explanation-for-absolutely-anyone/#5751cd8f1245
59 | P a g e
Purushottam Tiwari, 1828469
Marsh, W. E., 1993. PR0DUCTI0N TOOL. Decision tree analysis: Drawing sime of the uncertainty
out if decision making, 1(4), p. 17.
Milos Bujisic, V. B. ,. H. G. P., 2016. The effect of weather factors on restaurant sales. Journal of
Foodservice Business Research, pp. 1-2.
Milos Bujisic, V. B. H. G. P., 2016. The effect of weather factors on restaurant sales. Journal of
Foodservice Business Research, pp. 1-3.
Newman, C., Agioutantis, Z. & Schaefer, N., 2018. A New Generation of Web-Based Applications
for Mine Design, s.l.: Department of Mining Engineering University of Kentucky Lexington, KY.
Norio Baba, O.-K. A.-O. O. P., 2000. Utilization of Artificial Neural Networks & GAS for
Constructing an Intelligent Sales Prediction System. Utilization of Artificial Neural Networks &
GAS for Constructing an Intelligent Sales Prediction System, pp. 565-566.
Rarh, F., Pojee, D., Zulphekari, S. & Shah, V., 2017. Restaurant table reservation using time-
series prediction. Restaurant table reservation using time-series prediction, p. 153.
Rico, D., 2012. Architecture and Design Practices for Agile Project Management. [Online]
Available at: https://www.projectmanagement.com/articles/274313/Architecture-and-Design-
Practices-for-Agile-Project-Management
School of Economics and Management, W. P. U., 2010. A prediction and influence factor analysis
of China's food production. A prediction and influence factor analysis of China's food production
, p. 1.
60 | P a g e
Purushottam Tiwari, 1828469
Uyanik, G. K. & Guler, N., 2013. A Study on Multiple Linear Regression Analysis. A Study on
Multiple Linear Regression Analysis, I(4), pp. 1-2.
Vashishtha, S., 2008. Preparing for Agile Maintenance – Knowledge Management. [Online]
Available at: http://blog.xebia.com/preparing-for-agile-maintenance-knowledge-management/
Xinliang Liu, D. S., 2016. A STUDY ON THE IMPACT OF ONLINE TAKEOUT BASED ON THE
BAIDU INDEX ON THE MANAGEMENT OF UNIVERSITY CAFETERIA. A STUDY ON THE
IMPACT OF ONLINE TAKEOUT BASED ON THE BAIDU INDEX ON THE MANAGEMENT OF
UNIVERSITY CAFETERIA , p. 182.
Zou, K. H., Tuncali, K. & Silverman, S. G., 2003. Statistical Concepts Series. Correlation and
Simple LinearRegression, 10.1148(227:617– 628), pp. 1-2.
61 | P a g e
Purushottam Tiwari, 1828469
Appendix:
62 | P a g e
Purushottam Tiwari, 1828469
63 | P a g e
Purushottam Tiwari, 1828469
64 | P a g e
Purushottam Tiwari, 1828469
65 | P a g e
Purushottam Tiwari, 1828469
66 | P a g e
Purushottam Tiwari, 1828469
67 | P a g e