Prepared by Dr.

Anita Brigit Mathew

08-03-2024 Prepared by Dr. Anita Brigit Mathew 1
Module - 5 (Data Science Toolkits for Business
Analytics)
•Clustering - K-Means, DBSCAN,
Agglomerative and Hierarchical, Decision
Tree – ID3, Factor Analysis, and
Segmentation Analysis.
•Build spread sheet models, analysis using
spread sheets – What-if analysis, Break even
analysis.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 2
Clustering
1. K-Means
2. Agglomerative and Hierarchical
3. DBSCAN
4. Decision Tree – ID3
5. Factor Analysis
6. Segmentation Analysis
08-03-2024 Prepared by Dr. Anita Brigit Mathew 3
08-03-2024 Prepared by Dr. Anita Brigit Mathew 4
08-03-2024 Prepared by Dr. Anita Brigit Mathew 5
08-03-2024 Prepared by Dr. Anita Brigit Mathew 6
08-03-2024 Prepared by Dr. Anita Brigit Mathew 7
08-03-2024 Prepared by Dr. Anita Brigit Mathew 8
08-03-2024 Prepared by Dr. Anita Brigit Mathew 9
08-03-2024 Prepared by Dr. Anita Brigit Mathew 10
INITIAL POINTS AS PER DATA GIVEN (FROM PREVIOUS TABLE)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 11

08-03-2024 Prepared by Dr. Anita Brigit Mathew 12
08-03-2024 Prepared by Dr. Anita Brigit Mathew 13
08-03-2024 Prepared by Dr. Anita Brigit Mathew 14
08-03-2024 Prepared by Dr. Anita Brigit Mathew 15
 RESULT
OBTAINED

08-03-2024 Prepared by Dr. Anita Brigit Mathew 16

 SIMILARLY,
COMPUTE EUCLIDEAN DISTANCE BETWEEN ALL PAIR OF POINTS

NOTE: UPPER AND LOWER SIDE HAS SAME VALUES SO I HAVE PUT ONLY IN LOWER SIDE
08-03-2024 Prepared by Dr. Anita Brigit Mathew 17
 HERE, WE ARE USING SINGLE LINKAGE TECHNIQUE

MINIMUM VALUE D(P3,P6) SINGLE

LINKAGE

08-03-2024 Prepared by Dr. Anita Brigit Mathew 18

 CORRESPONDING DENDOGRAM FOR THE ABOVE DISTANCE D(P3,P6)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 19

 CALCUATE P3,P6 (NEW)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 20

08-03-2024 Prepared by Dr. Anita Brigit Mathew 21
08-03-2024 Prepared by Dr. Anita Brigit Mathew 22
08-03-2024 Prepared by Dr. Anita Brigit Mathew 23
08-03-2024 Prepared by Dr. Anita Brigit Mathew 24
08-03-2024 Prepared by Dr. Anita Brigit Mathew 25
 ANYONE WE CAN TAKE, I HAVE TAKEN THE FIRST ONE

08-03-2024 Prepared by Dr. Anita Brigit Mathew 26

 DISTANCE BETWEEN
P2 &P5 HENCE NEW CUSTER
OBTAINED

08-03-2024 Prepared by Dr. Anita Brigit Mathew 27

08-03-2024 Prepared by Dr. Anita Brigit Mathew 28
 NEW CLUSTER P2, P5
RECALCULATE NEW
DISTANCE MATRIX

08-03-2024 Prepared by Dr. Anita Brigit Mathew 29

08-03-2024 Prepared by Dr. Anita Brigit Mathew 30
08-03-2024 Prepared by Dr. Anita Brigit Mathew 31
08-03-2024 Prepared by Dr. Anita Brigit Mathew 32
08-03-2024 Prepared by Dr. Anita Brigit Mathew 33
 Re-calculate
new matrix

08-03-2024 Prepared by Dr. Anita Brigit Mathew 34

08-03-2024 Prepared by Dr. Anita Brigit Mathew 35
08-03-2024 Prepared by Dr. Anita Brigit Mathew 36
08-03-2024 Prepared by Dr. Anita Brigit Mathew 37
08-03-2024 Prepared by Dr. Anita Brigit Mathew 38
08-03-2024 Prepared by Dr. Anita Brigit Mathew 39
08-03-2024 Prepared by Dr. Anita Brigit Mathew 40
08-03-2024 Prepared by Dr. Anita Brigit Mathew 41
08-03-2024 Prepared by Dr. Anita Brigit Mathew 42
08-03-2024 Prepared by Dr. Anita Brigit Mathew 43
08-03-2024 Prepared by Dr. Anita Brigit Mathew 44
08-03-2024 Prepared by Dr. Anita Brigit Mathew 45
08-03-2024 Prepared by Dr. Anita Brigit Mathew 46
08-03-2024 Prepared by Dr. Anita Brigit Mathew 47
08-03-2024 Prepared by Dr. Anita Brigit Mathew 48
08-03-2024 Prepared by Dr. Anita Brigit Mathew 49
08-03-2024 Prepared by Dr. Anita Brigit Mathew 50
08-03-2024 Prepared by Dr. Anita Brigit Mathew 51
08-03-2024 Prepared by Dr. Anita Brigit Mathew 52
08-03-2024 Prepared by Dr. Anita Brigit Mathew 53
08-03-2024 Prepared by Dr. Anita Brigit Mathew 54
08-03-2024 Prepared by Dr. Anita Brigit Mathew 55
08-03-2024 Prepared by Dr. Anita Brigit Mathew 56
08-03-2024 Prepared by Dr. Anita Brigit Mathew 57
08-03-2024 Prepared by Dr. Anita Brigit Mathew 58
08-03-2024 Prepared by Dr. Anita Brigit Mathew 59
08-03-2024 Prepared by Dr. Anita Brigit Mathew 60
08-03-2024 Prepared by Dr. Anita Brigit Mathew 61
08-03-2024 Prepared by Dr. Anita Brigit Mathew 62
 Nearest to P1

08-03-2024 Prepared by Dr. Anita Brigit Mathew 63

 Nearest Neighbours

08-03-2024 Prepared by Dr. Anita Brigit Mathew 64

 Now find core,
border, and noise
data points

08-03-2024 Prepared by Dr. Anita Brigit Mathew 65

08-03-2024 Prepared by Dr. Anita Brigit Mathew 66
08-03-2024 Prepared by Dr. Anita Brigit Mathew 67
 3
clusters

Remains noise,
outlier

08-03-2024 Prepared by Dr. Anita Brigit Mathew 68

08-03-2024 Prepared by Dr. Anita Brigit Mathew 69
08-03-2024 Prepared by Dr. Anita Brigit Mathew 70
08-03-2024 Prepared by Dr. Anita Brigit Mathew 71
08-03-2024 Prepared by Dr. Anita Brigit Mathew 72
 What is a Decision Tree?
1. A decision tree is a flowchart-like representation, with
internal nodes representing features, branches
representing rules, and leaf nodes representing algorithm
results.
2. This versatile supervised machine-learning algorithm
applies to both classification and regression problems, ie
and power.
3. Decision trees are valued for their interpretability, as the
rules they generate are easy to understand.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 73
 What is Iterative Dichotomiser3 Algorithm?
1. Thе ID3 (Iterative Dichotomiser 3) algorithm is a classic decision tree
algorithm used for both classification and regression tasks.
2. ID3 deals primarily with categorical properties, which means that it can
efficiently handle objects with a discrete set of values.
3. This property is consistent with its suitability for problems where the input
features are categorical rather than continuous.
4. One of the strengths of ID3 is its ability to generate interpretable decision
trees.
5. The resulting tree structure is easily understood and visualized, providing
insight into the decision-making process.
6. However, ID3 can be sensitive to noisy data and prone to overfitting,
capturing details in the training data that may not adequately account for
new unseen data.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 74
 ID3 Algorithm - How ID3 Works?
1. Selecting the Best Attribute
ID3 employs the concept of entropy and information gain to determine the attribute that best separates
the data. Entropy measures the impurity or randomness in the dataset.
The algorithm calculates the entropy of each attribute and selects the one that results in the most
significant information gain when used for splitting the data.
2. Creating Tree Nodes
The chosen attribute is used to split the dataset into subsets based on its distinct values.
For each subset, ID3 recurses to find the next best attribute to further partition the data, forming
branches and new nodes accordingly.
3. Stopping Criteria
The recursion continues until one of the stopping criteria is met, such as when all instances in a branch
belong to the same class or when all attributes have been used for splitting.
4. Handling Missing Values
ID3 can handle missing attribute values by employing various strategies like attribute mean/mode
substitution or using majority class values.
5. Tree Pruning
Pruning is a technique to prevent overfitting. While not directly included in ID3, post-processing
techniques or variations like C4.5 incorporate pruning to improve the tree’s generalization.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 75
Mathematical Concepts of ID3 Algorithm

08-03-2024 Prepared by Dr. Anita Brigit Mathew 76

Mathematical Concepts of ID3 Algorithm
contd..

08-03-2024 Prepared by Dr. Anita Brigit Mathew 77

Mathematical Concepts of ID3 Algorithm
contd..

08-03-2024 Prepared by Dr. Anita Brigit Mathew 78

 Advantages and Limitations of ID3
Advantages
Interpretability: Decision trees generated by ID3 are easily interpretable, making
them suitable for explaining decisions to non-technical stakeholders.
Handles Categorical Data: ID3 can effectively handle categorical attributes without
requiring explicit data preprocessing steps.
Computationally Inexpensive: The algorithm is relatively straightforward and
computationally less expensive compared to some complex models.
Limitations
Overfitting: ID3 tends to create complex trees that may overfit the training data,
impacting generalization to unseen instances.
Sensitive to Noise: Noise or outliers in the data can lead to the creation of non-
optimal or incorrect splits.
Binary Trees Only: ID3 constructs binary trees, limiting its ability to represent more
complex relationships present in the data directly.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 79
 Factor Analysis
1. Factor Analysis is a technique reducing the huge number of variables into a
few numbers of factors is known as factoring of the data, and managing
which data is to be present in sheet comes under factor analysis.
2. It is completely a statistical approach that is also used to describe
fluctuations among the observed and correlated variables in terms of a
potentially lower number of unobserved variables called factors.
3. The factor analysis technique extracts the maximum common variance from
all the variables and puts them into a common score.
4. The belief behind factor analysis technique is that the information gained
about the interdependencies between observed variables can be used later
to reduce the set of variables in a dataset.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 80

 Factor Analysis contd..
• Factor analysis is a very effective tool for inspecting changeable
relationships for complex concepts such as social status,
economic status, dietary patterns, psychological scales, biology,
psychometrics, personality theories, marketing, product
management, operations research, finance, etc.
• It can help a researcher to investigate the concepts that are not
easily measured in a much easier and quicker way directly by
the cave in a large number of variables into a few easily
interpretable fundamental factors.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 81

08-03-2024 Prepared by Dr. Anita Brigit Mathew 82
08-03-2024 Prepared by Dr. Anita Brigit Mathew 83
08-03-2024 Prepared by Dr. Anita Brigit Mathew 84
08-03-2024 Prepared by Dr. Anita Brigit Mathew 85
08-03-2024 Prepared by Dr. Anita Brigit Mathew 86
 Types of factor analysis
1. Exploratory factor analysis (EFA) : used to identify composite inter-relationships among items
and group items that are the part of uniting concepts. The Analyst can’t make any prior
assumptions about the relationships among factors. It is also used to find the fundamental
structure of a huge set of variables. It lessens the large data to a much smaller set of summary
variables. Basic assumption is that any observed variable is directly associated with any factor.
2. Similarities with CFA are:
1. Evaluate the internal reliability of an amount.
2. Examine the factors represented by item sets. They presume that the factors aren’t
correlated.
3. Investigate the grade/class of each item.
3. EFA is a data-driven approach, which allows all items to load on all the factors, while in CFA
you need to specify which factors are required to load. EFA is really a nice choice if you have
no idea about what common factors might exist. EFA is able to generate a huge number of
possible models for your data, something which is not possible is, if a researcher has to specify
factors.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 87
1. Confirmatory factor analysis (CFA) : It is a more
complex(composite) approach that tests the theory that the items
are associated with specific factors. Confirmatory Factor Analysis
uses a properly structured equation model to test on the factors for
the evaluation of relationships between observed variables and
unobserved variables. Basic assumption is that each factor is
associated with a particular set of observed variables.
2. Confirmatory Factor Analysis provides information about the
standard quality of the number of factors that are required to
represent the data set. Using Confirmatory Factor Analysis, you can
define the total number of factors required. For example,
Confirmatory Factor Analysis is able to answer questions like Does
my thousand question survey can able to measure accurately the
one specific factor.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 88
1. Multiple Factor Analysis : This type of Factor Analysis is used when
your variables are structured in changeable groups. For example,
you may have a teenager’s health questionnaire with several points
like sleeping patterns, wrong addictions, psychological health,
mobile phone addiction, or learning disabilities. The Multiple
Factor Analysis is performed in two steps which are:-
2. Firstly, the Principal Component Analysis will perform on each and
every section of the data. Further, this can give a useful eigenvalue,
which is actually used to normalize the data sets for further use.
3. The newly formed data sets are going to merge into a distinctive
matrix and then global PCA is performed.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 89

• Generalized Procrustes Analysis (GPA) : The analysis is actually a
suggested way to compare the two approximate sets of
configurations and shapes, which were originally developed to
equivalent to the two solutions from Factor Analysis, this technique
was actually used to extend the GP Analysis so that more than two
shapes could be compared in many ways. The shapes are properly
aligned to achieve the target shape. Mainly GPA (Generalized
Procrustes Analysis) uses geometric transformations. Geometric
progressions are :
• Isotropic rescaling,
• Reflection,
• Rotation,
• Translation of matrices to compare the sets of data.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 90
•factors are created with equality; some factors
have more weights some have low. In a simple
example, imagine your car company says Maruti
Suzuki is conducting a survey includes, using –
telephonic survey, physical survey, google forms,
etc. for customer satisfaction and the results show
the following factor loadings.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 91

Performing Factor Analysis
# Create factor analysis object and perform factor
analysis
fa = FactorAnalyzer()
[Link](df, 6, rotation="varimax")
[Link]

08-03-2024 Prepared by Dr. Anita Brigit Mathew 92

08-03-2024 Prepared by Dr. Anita Brigit Mathew 93
 Factor analysis involves several steps:
1. Data preparation: The data are usually standardized
(i.e., scaled) to make sure that the variables are on a
common scale and have equal weight in the analysis.
2. Factor Extraction: The factors are identified based on
their ability to explain the variance in the data. There
are several methods for extracting factors, including
principal components analysis (PCA), maximum
likelihood estimate(MLE), and minimum residuals
(MR).
08-03-2024 Prepared by Dr. Anita Brigit Mathew 94
 Contd..
3. Factor Rotation: The factors are usually rotated to
make their interpretation easier. The most common
method of rotation is Varimax rotation, which tries
to maximize the variance of the factor loadings.
4. Factor interpretation: The final step involves
interpreting the factors and their loadings (i.e., the
correlation between each variable and each factor).
The loadings represent the degree to which each
variable is associated with each factor.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 95
 code
# Load the dataset
data(iris)
# View the first few rows of the dataset
head(iris)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 96

 Code contd..
Data Preparation - Before factor analysis, we need to
prepare the data by scaling the variables to have a mean
of zero and a standard deviation of one. This is important
because factor analysis is sensitive to differences in scale
between variables.
# Scale the data
iris_scaled <- scale(iris[,1:4])

08-03-2024 Prepared by Dr. Anita Brigit Mathew 97

 Code contd..
Determining the Number of Factors - The next step is to
determine the number of factors to extract from the
data. This can be done using a variety of methods, such
as the Kaiser criterion, scree plot, or parallel analysis. In
this example, we will use the Kaiser criterion, which
suggests extracting factors with eigenvalues greater than
one.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 98

 Code contd..
# Perform factor analysis
library(psych)
fa <- fa(r = iris_scaled, nfactors = 4, rotate = "varimax")
summary(fa)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 99

Interpreting the Results of Factor Analysis
Once the factor analysis is complete, we can interpret
the results by examining the factor loadings, which
represent the correlations between the observed
variables and the extracted factors. In general, loadings
greater than 0.4 or 0.5 are considered significant.
# View the factor loadings
fa$loadings

08-03-2024 Prepared by Dr. Anita Brigit Mathew 100

08-03-2024 Prepared by Dr. Anita Brigit Mathew 101
Validating the Results of Factor Analysis
1. It is important to validate the results of the factor
analysis by checking the assumptions of the
technique, such as normality and linearity.
2. It is important to examine the factor structure for
different subsets of the data to ensure that the
results are consistent and stable.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 102

# examine factor structure for different subsets of the data
subset1 <- subset(iris[,1:4], iris$[Link] <
mean(iris$[Link]))
fa1 <- fa(subset1, nfactors = 4)
print(fa1)
subset2 <- subset(iris[,1:4], iris$[Link] >=
mean(iris$[Link]))
fa2 <- fa(subset2, nfactors = 4)
print(fa2)
print(fa$Vaccounted) # display variance explained by each
factor
08-03-2024 Prepared by Dr. Anita Brigit Mathew 103
08-03-2024 Prepared by Dr. Anita Brigit Mathew 104
Factor Analysis using factanal( ) function:
The factanal() function is used to perform factor analysis on a data set.
The factanal() function takes several arguments described below
Syntax: factanal(x, factors, rotation, scores, covmat)
where,
x – The data set to be analyzed.
factors – The number of factors to extract.
rotation – The rotation method to use. Popular rotation methods
include varimax, oblimin, and promax.
scores – Whether to compute factor scores for each observation.
covmat – A covariance matrix to use instead of the default correlation
matrix.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 105
The output of factanal() function includes several pieces of information,
including:
Uniquenesses: The amount of variance in each variable that is not accounted
for by the factors.
Loadings: The correlations between each variable and each factor.
Communalities: The amount of variance in each variable that is accounted for
by the factors.
Eigenvalues: The amount of variance explained by each factor.
Factor Correlations: The correlations between the factors.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 106

# Install the required package
[Link]("psych")
# Load the psych package for
# data analysis and visualization
library(psych)
# Load the mtcars dataset
data(mtcars)
# Perform factor analysis on the mtcars dataset
factor_analysis <- factanal(mtcars, factors = 3,
rotation = "varimax")
# Print the results
print(factor_analysis)
08-03-2024 Prepared by Dr. Anita Brigit Mathew 107
08-03-2024 Prepared by Dr. Anita Brigit Mathew 108
08-03-2024 Prepared by Dr. Anita Brigit Mathew 109
08-03-2024 Prepared by Dr. Anita Brigit Mathew 110
 Segmentation Analysis
1. Segmentation analysis is a marketing technique that allows you to
split your customers or products into different groups.
2. Segmentation analysis supports the following:

To create new products that satisfy the needs of different

consumers groups in the market
To successfully position yourself against your competitors when
entering a market or launching a product
To understand preferences and trends so you can target your
audience with the right marketing messages
08-03-2024 Prepared by Dr. Anita Brigit Mathew 111
 Why Segmentation Analysis?
For a good segmentation there are two important aspects: the
characteristics of the data and the algorithms applied to analyze it.
Segmentation Analysis uses a two-stage process to ensure that both
elements will be covered properly.
• Data Reduction - Data come from different sources, a thorough data pre-
processing stage prior to running of any algorithms is done.
• Ensemble segmentation - After we have our final data set, we proceed to
apply the clustering algorithms. In some cases, given the nature of the
data, some algorithms are not appropriate to identify the patterns of
similarity, and in some others, two algorithms can lead to different
segmentation results.
• For instance, k-means would put consumer A and C in the same segment
and B in another segment whereas latent class and hierarchical clustering
would put consumer A and B in the same segment and not C.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 112
How does our unique ensemble clustering
approach work?
• The approach starts by creating micro-segments based only on a priori
group of variables such as behavioral data, attitudes, barriers, etc.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 113

In order to create the segments, our ensemble approach combines different
techniques such as

1. K-means: a method of vector quantization, that aims to partition n

observations into k clusters in which each observation belongs to the cluster
with the nearest mean, serving as a prototype of the cluster.
2. Latent Class: A class that relates a set of observed multivariate variables to
be characterized by a pattern of conditional probabilities that indicate the
chance that variables take on certain values.
3. Hierarchical Clustering: a method of cluster analysis which seeks to build a
hierarchy of clusters.
4. Random Forests: A random forest sees prediction as a kind of tree. Instead
of a tree splitting into branches, we split the data using attributes. These
splits grow from each other, with a first level split and then a second split of
that,
08-03-2024creating a tree-like structure
Prepared by of sequential
Dr. Anita Brigit Mathew data splits. 114
 What are the steps to perform Customer
Segmentation Analysis?
1. Identify your Customer Segmentation goals – objectives to segment the
customers
2. Know your Customers - Understand the Customer base through their
responses.
3. Collect and Analyze Customer Data – Collect Customer Data that is relevant
to the Segmentation Criteria.
4. Identify and Evaluate Segments – Create a detailed profile of each segment,
including information about their demographics, behaviors, and interaction
patterns.
5. Take action on specific segments – Develop a strategy for targeting each
segment,
08-03-2024
including tailored messaging, products and promotions.
Prepared by Dr. Anita Brigit Mathew 115
 3 ways that you can use to confirm if your
customer segmentation analysis is on track?
1. Ensuring that implementing customer segmentation analysis
works well for your brand is crucial.
2. Monitor Marketing Efforts -Use Social Media Analytics to
monitor customer engagement with your brand on different
platforms
3. Keep a track on Governance strategies – Test different strategies
for every customer segment to see what works and doesn’t and
make adjustments accordingly.
4. Align Segmentation Variance with Business goals – use metrics
08-03-2024 Prepared by Dr. Anita Brigit Mathew 116
such as conversion rates.
3 Potential Challenges that you might face during the
process of Customer Segmentation analysis
[Link] of Resources – limited data, tech stack.
[Link] defined Segments – leads to
inaccurate or ineffective targeting of
customers.
[Link] in Integrating Segmentation – lack of
alignment between different or departments
within the organization – an important
challenge.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 117
 What-if Analysis?
What is What-if Analysis?
What-if analysis is a procedure in excel in which we work in tabular
form data. In the What-if analysis variety of values have been in the cell
of the excel sheet to see the result in different ways by not creating
different sheets. There are three tools of what-if analysis.
Tools of what-if analysis
There are three tools in what-if analysis:
1. Goal seek
2. Scenario manager
3. Data Table
Goal seek
• In goal seek we already know our output value we have to find the
correct input value. For example, if a student wants to know
his English marks and he knows all the rest of the marks and total
marks in all subjects.
 Break even analysis
A break-even analysis is an economic tool that is used to
determine the cost structure of a company or the number
of units that need to be sold to cover the cost.
Break-even is a circumstance where a company neither
makes a profit nor loss but recovers all the money spent.
The break-even analysis is used to examine the relation
between the fixed cost, variable cost, and revenue.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 151

08-03-2024 Prepared by Dr. Anita Brigit Mathew 152
08-03-2024 Prepared by Dr. Anita Brigit Mathew 153
08-03-2024 Prepared by Dr. Anita Brigit Mathew 154
08-03-2024 Prepared by Dr. Anita Brigit Mathew 155
08-03-2024 Prepared by Dr. Anita Brigit Mathew 156
 Importance of Break-Even Analysis
1. Manages the size of units to be sold - company or the owner comes to
know how many units need to be sold to cover the cost.
2. Budgeting and setting targets - Since the company or the owner knows at
which point a company can break-even, it is easy for them to fix a goal and
set a budget for the firm accordingly.
3. Manage the margin of safety - In a financial breakdown, the sales of a
company tend to decrease. The break-even analysis helps the company to
decide the least number of sales required to make profits.
4. Monitors and controls cost - Companies’ profit margin can be affected by
the fixed and variable cost. Therefore, the management can detect if any
effects are changing the cost.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 157

 Importance of Break-Even Analysis contd..
5. Helps to design pricing strategy - The break-even point
can be affected if there is any change in the pricing of a
product. Example, if the selling price is raised, then the
quantity of the product to be sold to break-even will be
reduced. Similarly, if the selling price is reduced, then a
company needs to sell extra to break-even.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 158

 Components of Break-Even Analysis
1. Fixed costs: These costs are also known as overhead costs. These
costs materialise once the financial activity of a business starts. The
fixed prices include taxes, salaries, rents, depreciation cost, labour
cost, interests, energy cost, etc.
2. Variable costs: These costs fluctuate and will decrease or increase
according to the volume of the production. These costs include
packaging cost, cost of raw material, fuel, and other materials related
to production.
3. Selling Price: Selling price is the amount that the seller/company
charges the customers in exchange for their product or services. The
selling price is determined on the basis of raw materials used for
production, wages, fixed expenses, etc.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 159
 Uses of Break-Even Analysis
1. New business/ Expansion of Business : For a new venture, a break-even analysis is
essential. It guides the management with pricing strategy/selling price and is
practical about the cost. This analysis also gives an idea if the new business is
productive.
2. Manufacture new products: If an existing company is going to launch a new
product, then they still have to focus on a break-even analysis before starting and
see if the product adds necessary expenditure to the company.
3. Change in business model: The break-even analysis works even if there is a change
in any business model like shifting from retail business to wholesale business. This
analysis will help the company to determine if the selling price of a product needs
to change.
4. Lowering Prices: Sometimes, businesses need to lower down the price of their
product so that they can increase their sale and beat the competitors. So, when
lowering pricing, businesses need to figure out how many more units they need to
sell to offset or make up a price decrease.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 160
08-03-2024 Prepared by Dr. Anita Brigit Mathew 161
Break-Even Analysis Formula

08-03-2024 Prepared by Dr. Anita Brigit Mathew 162

 Example:
Particulars Amount (in ₹)
Fixed Expense 2,00,000
Variable Expenses 4/unit
Selling Price 24

Solution:
Here, Fixed Cost = ₹2,00,000; Variable Expense = ₹4 per
unit; and Selling Price = ₹24
08-03-2024 Prepared by Dr. Anita Brigit Mathew 163
Break-even Point = 10,000 units
It means that the company would need to sell 10,000
units of the product to attain break-even.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 164

 Graphical Presentation of Break-even point
• Break-even Point - The point where total revenue is the same as the total cost
is known as Break-even Point. At this point, the firm is able to meet all of its
costs.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 165

Contd..
X-axis shows units being sold and Y-axis shows the
revenue made.
The cost line shows the total cost that occurs during
the production process, the fixed cost line shows the
occurrence of fixed costs, and the revenue line shows
the total sales being made.
The intersection of the revenue curve and cost curve
determines the break-even point; i.e., point E.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 166
What is Break-even Point and Shut-down Point?

08-03-2024 Prepared by Dr. Anita Brigit Mathew 167

08-03-2024 Prepared by Dr. Anita Brigit Mathew 168
08-03-2024 Prepared by Dr. Anita Brigit Mathew 169
 Contd..
• The break-even point is attained when TR = TC
• By dividing both sides by Q (Output), the result will be

Hence, it can be concluded that the break-even point is a point

where TR = TC or AR = AC.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 170
08-03-2024 Prepared by Dr. Anita Brigit Mathew 171
Limitations of Break Even Chart

08-03-2024 Prepared by Dr. Anita Brigit Mathew 172

 Shut-Down Point

The situation when a firm is able to cover only its variable

costs is known as Shut-down Point. At this point, the total
revenue received from the sale of goods is the same as the
total variable costs of production; i.e.,
TR = TVC

08-03-2024 Prepared by Dr. Anita Brigit Mathew 173

• At the shut-down point, a firm incurs fixed cost loss. Even though
there is a fixed cost loss, the firm does not stop production as the
fixed cost will still be there. However, if the price or AR falls more
and is unable to meet even its average variable cost, then the firm
will have to shut down its operations.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 174

08-03-2024 Prepared by Dr. Anita Brigit Mathew 175
08-03-2024 Prepared by Dr. Anita Brigit Mathew 176
08-03-2024 Prepared by Dr. Anita Brigit Mathew 177
08-03-2024 Prepared by Dr. Anita Brigit Mathew 178
 Example of break-even analysis
Company X sells a pen. The company first determined the fixed costs,
which include a lease, property tax, and salaries. They sum up to
₹1,00,000. The variable cost linked with manufacturing one pen is ₹2
per unit. So, the pen is sold at a premium price of ₹10.
Therefore, to determine the break-even point of Company X, the
premium pen will be: Break-even point = Fixed cost/Price per cost –
Variable cost
= ₹1,00,000/(₹12 – ₹2)
= 1,00,000/10
= 10,000
Therefore, given the variable costs, fixed costs, and selling price of the
pen, company X would need to sell 10,000 units of pens to break-even.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 179
08-03-2024 Prepared by Dr. Anita Brigit Mathew 180
08-03-2024 Prepared by Dr. Anita Brigit Mathew 181
08-03-2024 Prepared by Dr. Anita Brigit Mathew 182
08-03-2024 Prepared by Dr. Anita Brigit Mathew 183
08-03-2024 Prepared by Dr. Anita Brigit Mathew 184
08-03-2024 Prepared by Dr. Anita Brigit Mathew 185
08-03-2024 Prepared by Dr. Anita Brigit Mathew 186
Break-Even Analysis: Problem with Solution # 2.
From the following data, you are required to calculate:
(a) P/V ratio
(b) Break-even sales with the help of P/V ratio.
(c) Sales required to earn a profit of Rs. 4,50,000
Fixed Expenses = Rs. 90,000
Variable Cost per unit:
Direct Material = Rs. 5
Direct Labour = Rs. 2
Direct Overheads = 100% of Direct Labour
Selling Price per unit = Rs. 12.
Solution:
08-03-2024 Prepared by Dr. Anita Brigit Mathew 187
Problems on Break-Even Analysis (With Solution)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 188

 Break-Even Analysis: Problem with Solution # 3.
• From the following data, you are required to calculate break-even point and
net sales value at this point:

• If sales are 10% and 25% above the break even volume, determine the net
profits.
• Solution:

08-03-2024 Prepared by Dr. Anita Brigit Mathew 189

08-03-2024 Prepared by Dr. Anita Brigit Mathew 190
08-03-2024 Prepared by Dr. Anita Brigit Mathew 191
Build spread sheet models
• Analysis using spread sheets

08-03-2024 Prepared by Dr. Anita Brigit Mathew 192

 Creating a Data Model in Excel
1. In Excel, a data model is a form of the data table in which two or
more tables are linked by a common or many data series.
2. Tables and data from many other sheets or sources are combined
in the data model to generate a single table that can access data
from all tables.
3. A Data Model enables you to combine data from different tables,
thereby creating a relational data source within an Excel
spreadsheet.
4. Data Models are utilized openly in Excel, supplying tabular data
for PivotTables and PivotCharts.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 193
 Data Model in Excel
•We have three datasets: one with customer
information, another with product information, and
the third with sales information.
•Dataset 1: It contains customer information with
the customer ID, customer, Gender, and region field.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 194

08-03-2024 Prepared by Dr. Anita Brigit Mathew 195
Dataset 2: It contains product information with the
product ID, category, size, and price field.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 196

Dataset 3: It contains sales information with the Sales
ID, Date, Customer ID, Product ID, and Quantity fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 197

Step By Step implementation of Data Model
• Step 1: In Excel, create a new blank Workbook. Then go to
Power Pivot on the top of the ribbon. Then select manage
from the Data Model group.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 198

Step 2: Power Pivot for excel sheet is open. Now go to
the home tab on the top of the ribbon and then
select From other sources from the Get External Data
group.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 199

08-03-2024 Prepared by Dr. Anita Brigit Mathew 200
Step 3: After selecting Table Import Wizard dialog box appears. Here select the Excel
file option from the Text files group and then click Next.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 201

Step 4: Here Browse the file path, where your file is stored.
Make sure to check the Use first row as column
header option and then again click Next.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 202

Step 5: Now it shows the customer sheet just check it if it is
not checked and then again click on FINISH.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 203

Step 6: Now sheet 1 is successfully imported with all the
rows in the Power Pivot table. Now just click on Close.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 204

Step 7: Now as you can see Customer table is
successfully imported with all the fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 205

Step 8: Now you need to select the From Other Sources option and follow the same
steps again for the Product dataset. In this, you can see after doing all the steps it
automatically creates a Product sheet with all the fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 206

Step 9: Now again you need to select the From Other Sources option and follow the
same steps again that are used in the customer dataset for the Sales dataset. Now,
you can see after doing all the steps it automatically creates a Sales sheet with all the
fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 207

Step 10: Now go to the home tab on the top of the ribbon
and then select Diagram view from the view group.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 208

Step 11: Now you can see it creates a dataset of all
three tables i.e., Customer, Sales, and Product.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 209

Step 12: Now you need to connect all three datasets with each other. First, we are
connecting the customer Id field from the sales Table to the customer table because
it is common in the sales Table and the customer table. Second, we are connecting
the product Id field from the sales Table to the product table because it is common in
the sales Table and the product table.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 210

Step 13: Go to the home tab and then select
the Pivot table option from the top of the ribbon.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 211

Step 14: Create PivotTable dialog box appears. Here
just select the new worksheet and then click on OK.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 212

Step 15: Now in the Excel sheet pivot table is open with
the PivotTable fields pane that shows all three tables.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 213

Step 16: Just drag the region field of the customer table to
the Rows pane and the category field of the product table
to the Columns pane. Now it will show the Pivot table with
the region and the product fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 214

Step 17: Drag the Quantity field from the sales table to the Values pane. Then it
shows all the quantities according to the product and region and also it sums all the
quantities.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 215

 Analyse using Charts/Graphs
1. Data visualization isn’t just for presenting data, it’s useful for visualizing trends,
correlations and patterns in the data.
2. For most analyses, the three most important charts are:
3. Bar Charts
4. Scatter plots
5. Time series
6. How to quickly create charts in Excel:
• Select the data you want to visualize.
• Go to the “insert” tab. This is where most of your data analysis tools will be including
charts and pivot tables.
• Choose “recommended charts” and pick the one there if it suits your needs. Otherwise,
go to “all charts” and find a suitable one there. There should be plenty.
08-03-2024 Prepared by Dr. Anita Brigit Mathew 216
08-03-2024 Prepared by Dr. Anita Brigit Mathew 217
• Bar Charts:
• Bar charts are the bread and butter of data analysis. You'll be creating
hundreds of these!
• Bar charts are ideal for studying the relationship between 2 variables:
• A categorical variable like “gender, product, payment type”
• A numerical measurement like “cost, profits, quantity.”
• A bar chart will allow you to see the relationship between these
things, for instance: how does “payment type” affect “profits?”

08-03-2024 Prepared by Dr. Anita Brigit Mathew 218

• Scatter Plots
• Scatter plots allow you to see the correlation and distribution
between 2 numerical variables. For instance: customer purchase
power vs. household income.
• A line of best fit can be drawn to help make predictions about the
data. For example: “What would be a customer’s purchasing power if
their household income was $60,000?”
• How to create a line of best fit in Excel scatter plots:
• Create your scatterplot.
• Click on “Add Chart Element” at the top left.
• Choose Trendline -> Linear

08-03-2024 Prepared by Dr. Anita Brigit Mathew 219

08-03-2024 Prepared by Dr. Anita Brigit Mathew 220
How to Analyze Data in Excel

08-03-2024 Prepared by Dr. Anita Brigit Mathew 221

1. Load up the Analysis Toolpak add-in for Excel: File ->
Options (at the bottom left) -> Add-ins -> Go ->
Check the Analysis Toolpak and press OK.
2. Go to the “Data” tab and press “Analyze Data”
3. Choose the type of analysis you want to perform

08-03-2024 Prepared by Dr. Anita Brigit Mathew 222

Methods of Data Analysis
Charts
• Any set of information may be graphically represented in a chart. A
chart is a graphic representation of data that employs symbols to
represent the data, such as bars in a bar chart or lines in a line chart.
Excel has several different chart types available for you to choose
from, or you can use the Excel Recommended Charts option to look at
charts specifically made for your data and choose one of those.
• Step 1: Select a table. After that go to the Insert tab on the top of the
ribbon then in the charts group select any chart. Here we are going
to select a 3-D column chart.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 223

08-03-2024 Prepared by Dr. Anita Brigit Mathew 224
Step 2: As you can see, the excel table has been
converted to a 3-D column chart.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 225

 Conditional Formatting
• Patterns and trends in your data may be highlighted with the help of
conditional formatting. To use it, write rules that determine the format of
cells based on their values. In Excel for Windows, conditional formatting can
be applied to a set of cells, an Excel table, and even a PivotTable report. To
execute conditional formatting, adhere to the instructions listed below.
• Step 1: Select any column from the table. Here we are going to select a
Quarter column. After that go to the home tab on the top of the ribbon and
then in the styles group select conditional formatting and then in
the highlight cells rule select Greater than an option.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 226

08-03-2024 Prepared by Dr. Anita Brigit Mathew 227
Step 2: Then a greater than dialog box appears. Here
first write the quarter value and then select the color.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 228

Step 3: As you can see in the excel table Quarter column
change the color of the values that are greater than 6.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 229

Sorting - Step 1: Select any column from the table. Here we
are going to select a Months column. After that go to
the data tab on the top of the ribbon and then in the sort
and filters group select sort.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 230

Step 2: Then a sort dialog box appears. Here first select the
column, then select sort on, and then Order. After that click
OK.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 231

Step 3: Now as you can see the months column is
now arranged alphabetically.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 232

Filter- Step 1: Select any column from the table. Here we
are going to select a Sales column. After that go to the data
tab on the top of the ribbon and then in the sort and filters
group select filter.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 233

Step 2: The values in the sales column are then shown in a
drop-down box. Here we are going to select a number of
filters and then greater than.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 234

Step 3: Then a custom auto filler dialog box appears. Here
we are going to apply sales greater than 70 and then click
OK.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 235

Step 4: Now as you can see only the rows greater
than 70 are shown.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 236

• LEN = LEN quickly returns the character count in a
given cell. The LEN formula may be used to calculate
the number of characters needed in a cell to
distinguish between two different kinds of product
Stock Keeping Units, as seen in the example above.
When trying to discern between different Unique
Identifiers, which might occasionally be lengthy and
out of order, LEN is very crucial.
• LEN(Select Cell)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 237

Step 1: If we want to see the length of cell A2, for that we
need to write the function of length.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 238

Step 2: Now as you can see it shows the
length of the cell A2.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 239

• TRIM
• =TRIM function will remove all spaces from a cell, with the
exception of single spaces between words. The most
frequent application of this function is to get rid of trailing
spaces. When content is copied verbatim from another
source or when users insert spaces at the end of the text,
this is normal.
• =TRIM(Select Cell)

08-03-2024 Prepared by Dr. Anita Brigit Mathew 240

Step 1: If we want to remove all spaces from cell A2,
for that we need to write the function of trim.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 241

Step 2: Now as you can see after using the trim function,
it removes all spaces.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 242

• UPPER
• The Excel Text function “UPPER Function” will change
the text to all capital letters (UPPERCASE). As a result,
the function changes all of the characters in a text
string input to upper case.
• =UPPER(Text)
• Text (mandatory parameter): This is the text that we
wish to change to uppercase. Text can relate to a cell
or be a text string.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 243

Step 1: If we want to convert the A2 cell to upper
text, for that we need to write the upper function.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 244

Step 2: Now as you can see after using the upper
function, the text is changed to the upper text.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 245

• PROPER
• Under Excel Text functions, the PROPER Function is
listed. Any subsequent letters of text that come after a
character other than a letter will also be capitalized by
PROPER.
• =PROPER(Text)
• Text (mandatory parameter): A formula that returns
text, a cell reference, or text in quote marks must
surround the text you wish to partly capitalize.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 246

Step 1: If we want to convert the A2 cell to proper
text, for that we need to write the proper function.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 247

Step 2: Now as you can see after using the proper
function, the text is changed to the proper form.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 248

• COUNTIF
• Excel has a built-in function called COUNTIF that counts the given
cells. The COUNTIF function can be used in both straightforward
and sophisticated applications. The fundamental application of
counting particular numbers and words is covered in this.
• =COUNTIF(range,criteria)
• Range: The size of the cell range to count.
• Criteria: The standards by which cells are selected for counting.
• Step 1: Use the COUNTIF function on the range B2:B20 to get the
number of regions we have of each type.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 249

08-03-2024 Prepared by Dr. Anita Brigit Mathew 250
Step 2: The COUNTIF function will now be used to count
the different sorts of Regions in the range F5:F9.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 251

Step 3: Now as you can see the 4 East Region has been
correctly enumerated using the COUNTIF function.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 252

• VLOOKUP
• VLOOKUP is a built-in Excel function that permits searching across several
columns.
• =VLOOKUP(lookup_value, table_array, col_index_num, [range_lookup])
• Lookup_value: Choose the cell that will be used to input the search
criteria.
• Table_array: The whole table range, which includes each and every cell.
• Col_index_num: The information being searched for. The column’s number,
starting from the left, is the input.
• Range_lookup: FALSE if text (0), TRUE if numbers (1).
• Step 1: To locate the Festival names depending on their search ID, use the
VLOOKUP function. The Festival names in this instance are determined by
their search ID.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 253

08-03-2024 Prepared by Dr. Anita Brigit Mathew 254
Step 2: F5 was chosen as the lookup value. The search query is typed in this cell.
Table array, in this case, A2:C20, is designated as the table’s range. The col index
number is set to 3, which is entered. The information being searched is in the third
column from the left. Range lookup is entered as 0 (False).

08-03-2024 Prepared by Dr. Anita Brigit Mathew 255

Step 3: The #N/A value is what the function returns. This is
the result of the Search ID F5 having no value entered.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 256

Step 4: The Homegrown Festival, which has Search
ID 6, has been located through the VLOOKUP tool.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 257

• PIVOT TABLE
• In order to create the required report, a pivot table is a
statistics tool that condenses and reorganizes specific
columns and rows of data in a spreadsheet or database
table. The utility simply “pivots” or rotates the data to
examine it from various angles rather than altering the
spreadsheet or database itself.
• Step 1: Select any cell and then go to the home tab and
then select Pivot table.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 258

08-03-2024 Prepared by Dr. Anita Brigit Mathew 259
Step 2: Create Pivot table dialog box appears here
select the new worksheet and then click OK.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 260

Step 3: Now you can see it creates a pivot table.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 261

Step 4: Just drag the Country field to the row
area and the Days field to the value area.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 262

Step 5: Now you can see the proper pivot table
with Country and days fields.

08-03-2024 Prepared by Dr. Anita Brigit Mathew 263