Professional Documents
Culture Documents
Business Intelligence: Basics of The Course
Business Intelligence: Basics of The Course
INTELLIGENCE
BASICS OF THE COURSE
Teaching Scheme Examination Scheme
Lectures: 3 Hrs/ Week Class Test 1 :15 Marks
Credits : 3 Class Test 2 :15 Marks
Teacher’s Assessment : 10 Marks
End Semester Exam : 60 Marks
• Course Name – Business Intelligence
• Course Code – ITHS 1030
• Schemes -
BASICS OF THE COURSE
• PREREQUISITES:
NA
BASICS OF THE COURSE
• COURSE DESCRIPTION:
• To expose to the basics of Business
Intelligence System with an
understanding of modeling aspects
behind Business Intelligence
BASICS OF THE COURSE
• COURSE OUTCOMES :
• CO1 : Understand the need of BI & its
applications
• CO2 : Know the BI Life Cycle and its
techniques
• CO3 : Explore different tools and techniques
for analysis and decision making
• CO4 : Discuss Modelling and analysis of Data
reason
• BUSINESS INTELLIGENCE :
INTRODUCTION OF THE SUBJECT
• Business intelligence combines business
analytics, data mining, data visualization, data
tools and infrastructure, and best practices to
help organizations make more data-driven
decisions.
UNIT - I
BUSINESS
INTELLIGENCE
SYLLABUS
• Effective and timely decisions – Data,
information and knowledge – Role of
mathematical models
• Business intelligence architectures:
Cycle of a business intelligence analysis –
Enabling factors in business intelligence
projects
• Development of a business intelligence
system – Ethics and business
intelligence.
BUSINESS
INTELLIGENCE
BUSINESS INTELLIGENCE
• What is business intelligence?
• Business intelligence combines
business analytics, data mining, data
visualization, data tools and
infrastructure, and best practices to
help organizations make more
datadriven decisions.
BUSINESS INTELLIGENCE
• How business intelligence works?
BUSINESS INTELLIGENCE
• Gather the necessary data, analyze it, and
determine which actions to take to reach their
goals.
• Raw data is collected from business systems
• Data is processed and then stored in data
warehouses, the cloud, applications, and files.
• Once it’s stored, users can access the data,
starting the analysis process to answer
business questions
BUSINESS INTELLIGENCE
• BI platforms also offer data visualization
tools, which convert data into charts or
graphs, as well as presenting to any key
stakeholders or decision-makers.
BUSINESS INTELLIGENCE
• ADVANTAGES AND DISADVANTAGES OF BI :
• Some of the advantages of BI include:
– Data visibility
– Accurate reports
– Streamlined processes
• And disadvantages of BI include:
– Initial cost
– User resistance
– Data skills gap
MODELS
• TYPES OF MODELS :
–Mathematical Model
–Quantitative Model
–Linear Programming Model
–Normative Models –Descriptive
Models
MODELS
• BENEFITS OF MODELS :
1. Time compression
2. Easy model manipulation
3. Low cost of construction
4. Low cost of execution (especially that of errors)
5. Can model risk and uncertainty
6. Can model large and extremely complex systems
with possibly infinite solutions
7. Enhance and reinforce learning, and enhance
training.
MODELS
• SOLUTION APPROACHES
– Trial-and-Error
– Simulation
– Optimization
– Heuristics
MODELS
• MATHEMATICAL MODEL :
• Identify variables
• Establish equations describing their
relationships
• Simplifications through assumptions
• Balance model simplification and the
accurate representation of reality
MODELS
• QUANTITATIVE MODELS :
• Components of Quantitative Models :
– Decision Variables
– Uncontrollable Variables (and/or Parameters) –
Result (Outcome) Variables
– Mathematical Relationships or
– Symbolic or Qualitative Relationships
MODELS
• DECISION VARIABLES :
• Describe alternative courses of action
• The decision maker controls them
MODELS
• RESULT (OUTCOME) VARIABLES:
• Reflect the level of effectiveness of the
system
• Dependent variables
MODELS
• UNCONTROLLABLE VARIABLES OR
PARAMETERS :
• Factors that affect the result variables
• Not under the control of the decision
maker
• Generally part of the environment
• Some constrain the decision maker and
are called constraints
MODELS
• THE STRUCTURE OF QUANTITATIVE
MODELS :
• Mathematical expressions (e.g.,
equations or inequalities) connect
the components
• Simple financial model P = R - C
MODELS
• LINEAR PROGRAMMING MODEL:
• Components
Decision variables
Result variable
Uncontrollable variables (constraints)
MODELS
• NORMATIVE MODELS :
• The chosen alternative is demonstrably the
best of all (normally a good idea)
• Optimization process
• Normative decision theory based on
rational decision makers
MODELS
• Descriptive Models
• Describe things as they are, or as they are
believed to be
• Extremely useful in DSS for evaluating
the consequences of decisions and
scenarios
• No guarantee a solution is optimal
• Often a solution will be good enough
DECISION MAKING
DECISION MAKING
• Decision Making can be done under
following circumstances:
–Decision Making Under certainty
–Decision Making Under Risk
–Decision Making Under Uncertainty
DECISION MAKING
• DECISION MAKING UNDER CERTAINTY :
• Assumes complete knowledge available
(deterministic environment)
• Typically for structured problems with
short time horizons
• Sometimes DSS approach is needed for
certainty situations
• DECISION MAKING UNDER RISK :
DECISION MAKING
• Probabilistic or stochastic decision situation
• Must consider several possible outcomes for
each alternative, each with a probability
• Long-run probabilities of the occurrences of
the given outcomes are assumed known or
estimated
2. Gender
3. Human cognition
4. Decision styles
DECISION MAKING
1. Personality (Temperament) Types :
• Strong relationship between personality and
decision making
• Type helps explain how to best attack a problem
• Type indicates how to relate to other types
– important for team building
• Influences cognitive style and decision style
DECISION MAKING
2. Gender:
• Sometimes empirical testing indicates
gender differences in decision making
• Results are overwhelmingly
inconclusive
DECISION MAKING
3. Cognition:
• Activities by which an individual resolves
differences between an internalized view of the
environment and what actually exists in that
same environment
• INDIVIDUALS :
DECISION MAKING
• May still have conflicting objectives
• Decisions may be fully automated
• GROUPS:
• Most major decisions made by groups
DECISION MAKING
• Conflicting objectives are common • Variable size
• People from different departments
• People from different organizations
• The group decision-making process can be very
complicated
• Consider Group Support Systems (GSS)
• Design phase
PHASES OF THE DECISION-MAKING
– Representative model is constructed
– The model is validated and evaluation criteria
are set
PROCESS
• Choice phase
– Includes a proposed solution to the model
– If reasonable, move on to the
• Implementation phase
– Solution to the original problem
PHASES OF THE DECISION-MAKING
Failure: Return to the modeling process
NonprogrammedProgrammed Problems
Problems
INTELLIGENCE PHASE
• Problem Decomposition: Divide a complex
problem into (easier to solve) subproblems
Chunking (Salami)
• Some seemingly poorly structured
problems may have some highly structured
subproblems
DECISION MAKING: THE
DECISION MAKING: THE
INTELLIGENCE PHASE
• Problem Ownership Outcome:
Problem Statement
INTELLIGENCE PHASE
• Intelligence phase of decision-making process
involves searching the environment for
conditions calling or decisions.
• This is related with the identification and
formulation of the problem which is to be
solved by the decision.
• A problem is the gap between present state
of affairs and desired state of affairs on the
subject matter of decision.
DECISION MAKING: THE
INTELLIGENCE PHASE
• When a problem is identified, it remains
vague at the initial stage.
• In order to make it more clear and specific,
problem formulation is required so that
design and choice phases operate on the right
problem.
DECISION MAKING: THE
• At this stage, the problem identified earlier, is
defined more precisely and some complexity
is reduced.
INTELLIGENCE PHASE
• MacGrimmon and Taylor have suggested four
strategies for reducing complexity and
formulating a problem :
• 1. Determining the boundaries (clearly identifying
what is included in the problem).
DECISION MAKING: THE
• 2. Examining changes that may have precipitated
the problem.
• 3. Factoring the problem into smaller
subproblems.
• 4. Focusing on controllable elements.
INTELLIGENCE PHASE
• For this phase of decision making, information
requirement is in the form of exception
reporting, that is, what kind of deviation exists
DECISION MAKING: THE
between desired state of affairs and actual
state of affairs.
• Such type of information is provided by
structured information- systems that deliver a
wide variety of detailed information.
DECISION MAKING: THE DESIGN
PHASE
PHASE
• Generating, developing, and analyzing possible
courses of action
Includes
• Understanding the problem
• Testing solutions for feasibility
• A model is constructed, tested, and validated
DECISION MAKING: THE DESIGN
Modeling
• Conceptualization of the problem
• Abstraction to quantitative and/or qualitative forms
PHASE
• Design phase of decision making involves
generation of possible alternatives through
which the problem can be solved.
• A problem can be solved in several ways,
however, all the ways cannot be equally
satisfying.
DECISION MAKING: THE DESIGN
• Further, if there is only one way of solving a
problem, no question of decision arises.
PHASE
• Therefore, the decision maker must try to find out the
various alternatives available in order to get the most
satisfactory result of a decision.
• Identification of various alternatives not only serves the
purpose of selecting the most satisfactory one, but it
also avoids bottlenecks in operation as alternatives are
available if a particular decision goes wrong.
• However, it should be borne in mind that - it may not be
possible to consider all alternatives either because some
DECISION MAKING: THE DESIGN
of the alternatives cannot be considered for selection
because of obvious limitations of the decision maker or
information about all alternatives may not be available.
PHASE
• Therefore, while generating alternatives, the
concept of limiting factor should be applied.
• A limiting factor is one which stands in the way of
accomplishing a desired objective.
• If these factors are identified, managers will
confine their search for alternatives to those
which will overcome the limiting factors.
DECISION MAKING: THE DESIGN
• For example, if an organization has limitation in
raising sizable finances, it cannot consider
projects involving high investment.
PHASE
• A decision maker can use several sources for
identifying alternatives his own past experience,
practices followed by others, and using creative
techniques.
• Past experience applied in most cases of decision
making, takes into account the actions taken by
the decision maker in the past with obvious
DECISION MAKING: THE DESIGN
differences between the former challenges and
the present one.
• The successful action of the past may become an
alternative for the future.
PHASE
• This is a very simple approach but has obvious
limitations because there may be so much
chances in the decision context that old
action becomes totally irrelevant.
• Copying from the experiences of others is
another way of generating alternatives.
DECISION MAKING: THE DESIGN
• Thus, alternatives used by successful decision
makers can be thought of as alternatives of
decision making.
PHASE
• This is also practiced by many organizations after
making suitable amendments in the light of
changed decision context.
• Importing of technology from foreign countries
with suitable changes is good example of this
type of alternatives.
DECISION MAKING: THE DESIGN
• The third method of generating alternatives is
through creative process where various exercises
are taken to generate entirely new ideas.
PHASE
• The design phase of decision making may
require more intelligence so that the manager
can decide if a particular alternative is
suitable for solving the problem.
• This phase may entail more carefully specified
and directed information activities which are,
generally, provided by decision support
DECISION MAKING: THE DESIGN
systems as they operate on simple models
and can be operated with limited data.
DECISION MAKING: THE
IMPLEMENTATION PHASE
IMPLEMENTATION PHASE
Important Issues
• Resistance to change
DECISION SUPPORT
SYSTEM
DECISION SUPPORT SYSTEM
• Syllabus :
WHAT IS A DECISION SUPPORT
• How Decisions Are Supported, Decision
Support System Configurations, Decision
Support System Characteristics and
Capabilities, Decision Support System
Classifications, Components of Decision
Support Systems
SYSTEM (DSS)?
• A Decision Support System (DSS) is a
computerbased tool designed to aid individuals
and organizations in making informed decisions.
• It integrates data, models, and analytical tools to
solve complex problems.
• The primary purpose of a DSS is to provide timely
and relevant information & facilitate analysis to
help decision-makers evaluate potential
outcomes.
WHAT IS A DECISION SUPPORT
SYSTEM (DSS)?
WHAT IS A DECISION SUPPORT
SYSTEM (DSS)?
• A Decision Support System (DSS) is a
computerized tool that assists individuals and
organizations in making well-informed
decisions.
• It combines data analysis, modeling, and
interactive interfaces to tackle complex
problems and aid decision-makers in various
fields
WHAT IS A DECISION SUPPORT
SYSTEM (DSS)?
• DSSs offer real-time data access, scenario
simulation, and predictive analytics,
enabling users to explore multiple options
and their potential outcomes.
• By enhancing decision accuracy and reducing
uncertainty, DSSs play a crucial role in
strategic planning, operational efficiency, and
competitive advantage across industries.
DECISION SUPPORT SYSTEM
CHARACTERISTICS
DECISION SUPPORT SYSTEM
CHARACTERISTICS
• Interactive: DSSs provide an interactive interface
that allows users to manipulate data, adjust
parameters, and explore different scenarios.
Users can engage with the system in real-time
and receive instant feedback.
DECISION SUPPORT SYSTEM
• Support for Decision-Making: The primary
purpose of a DSS is to assist decision-makers in
making informed choices. DSSs provide relevant
data, analyses, and insights to facilitate
decisionmaking.
CHARACTERISTICS
• Modeling and Analysis: DSSs incorporate
various models, algorithms, and analytical
tools to process data and generate insights.
These tools aid in predicting outcomes,
identifying trends, and evaluating
alternatives.
• User-Friendly Interface: DSSs offer
userfriendly interfaces that make it accessible
to non-technical users. These interfaces often
include visualizations and easy-to-understand
reports.
DECISION SUPPORT SYSTEM
DECISION SUPPORT SYSTEM
CLASSIFICATIONS
CLASSIFICATIONS
• Types of DSS:
1. Model-Driven DSS:
• These systems use mathematical and analytical
models to support decision-making.
• They rely on data inputs and algorithms to
generate predictions, simulations, and
optimization solutions.
• Examples include financial forecasting systems
and inventory management tools.
DECISION SUPPORT SYSTEM
CLASSIFICATIONS
2. Data-Driven DSS:
• These DSSs focus on data analysis and
visualization to aid decisions.
• They help users explore patterns, trends, and
relationships in data through charts, graphs,
and reports.
• Business intelligence and data visualization
tools fall into this category.
DECISION SUPPORT SYSTEM
CLASSIFICATIONS
3. Document-Driven DSS:
• These DSSs manage and provide access to
textual information relevant to
decisionmaking.
• They can organize documents, reports, and
research papers, making them easily
accessible to users.
DECISION SUPPORT SYSTEM
CLASSIFICATIONS
4. Knowledge-Driven DSS:
• These systems incorporate expert knowledge
and rules to support decisions.
• They can answer queries, provide advice, and
offer recommendations based on predefined
rules and expertise.
• Medical diagnosis systems and legal advisory
systems are examples.
COMPONENTS OF DECISION
SUPPORT SYSTEMS
SYSTEMS
1. Data Management:
• This involves gathering, storing, and
organizing relevant data from various
sources.
COMPONENTS OF DECISION
SUPPORT
• It may include historical data, real-time
information, external databases, etc.
SYSTEMS
2. Modeling and Analysis Tools:
• DSSs use various models, algorithms, and
analytical techniques to process data and
generate insights.
COMPONENTS OF DECISION
SUPPORT
• These tools can include statistical
analysis, optimization algorithms,
forecasting models, and simulation
methods.
SYSTEMS
3. User Interface:
COMPONENTS OF DECISION
SUPPORT
• The user interface allows decisionmakers
to interact with the DSS.
• It presents data, visualizations, and
results in a user-friendly manner,
enabling users to input parameters, run
analyses, and interpret outcomes.
COMPONENTS OF DECISION
SUPPORT
SYSTEMS
4. Database Management System (DBMS):
• A DBMS manages the storage and
retrieval of data for the DSS.
• It ensures data integrity, security, and
efficient access to the required
information.
COMPONENTS OF DECISION
SUPPORT
SYSTEMS
5. Knowledge Base:
• This component stores domain-specific
knowledge, rules, and guidelines for
decision-making.
• It helps the DSS understand the context
and constraints of the problem.
COMPONENTS OF DECISION
SUPPORT
SYSTEMS
6. Communication and Collaboration
Tools:
• DSSs often support communication and
collaboration among team members.
COMPONENTS OF DECISION
SUPPORT
• They enable sharing of information,
analysis results, and scenarios,
facilitating group decision-making.
DECISION SUPPORT SYSTEM
APPLICATION BASED CATEGORIES
APPLICATION BASED CATEGORIES
• There are several ways to classify DSS based
on its applications.
• Not every DSS fits neatly into one of the
categories, but may be a mix of two or more
architectures.
DECISION SUPPORT SYSTEM
• Holsapple and Whinston classify DSS into the
following six frameworks:
APPLICATION BASED CATEGORIES
• Text-oriented DSS,
• Database-oriented DSS,
• Spreadsheet-oriented DSS,
• Solver-oriented DSS,
• Rule-oriented DSS, and
DECISION SUPPORT SYSTEM
• Compound DSS
APPLICATION BASED CATEGORIES
• Text Oriented DSS: contains information in
text form allowing documents to be
electronically created, revised and viewed as
needed.
• Database Oriented DSS: Driven by a
database of organized and highly structured
data.
DECISION SUPPORT SYSTEM
APPLICATION BASED CATEGORIES
• Spreadsheet Oriented DSS: contains information
in spread sheets. A spread sheet makes it easy to
create, view, or modify procedural knowledge. It
is also possible to instruct the system to execute
self-contained instructions.
• Solver Oriented DSS: based on an algorithm or
procedure written for performing certain
DECISION SUPPORT SYSTEM
calculations and executing a particular program
type.
APPLICATION BASED CATEGORIES
• Rules Oriented DSS: follows certain
procedures adopted as rules.
• Compound DSS : A compound DSS is the
most popular classification for a DSS; it is a
hybrid system that includes two or more of
the five basic structures.
DECISION SUPPORT SYSTEM
CAPABILITIES
DECISION SUPPORT SYSTEM
CAPABILITIES
• A decision support system increases the speed
and efficiency of decision-making activities. It is
possible, as a DSS can collect and analyze
realtime data.
• It promotes training within the organization, as
specific skills must be developed to implement
and run a DSS within an organization.
• It automates monotonous managerial
processes, which means more of the manager’s
time can be spent on decision-making.
• It improves interpersonal communication within
the organization.
DECISION SUPPORT SYSTEM
CAPABILITIES
• What-if analysis
• Goal-seeking
• Sensitivity analysis • Exception reporting
analysis
• More capabilities, such as:
– Graphical analysis, forecasting, simulation,
statistical analysis, and modeling analysis
APPLICATIONS
APPLICATIONS
• Business Management:
• DSS aids in strategic planning, resource
allocation, and performance analysis for
businesses.
• It assists in setting goals, evaluating
alternatives, and optimizing operational
processes.
APPLICATIONS
• Healthcare:
• DSS supports medical professionals in
diagnosis, treatment planning, and patient
management.
• It helps doctors make informed decisions by
providing access to patient records, medical
literature, and clinical guidelines.
APPLICATIONS
• Finance:
• DSS is used for financial forecasting, risk
assessment, portfolio management, and
investment analysis.
• It helps financial analysts make informed
decisions about investment opportunities
and market trends.
APPLICATIONS
• Supply Chain Management:
• DSS assists inventory management,
demand forecasting, and logistics
optimization.
• It helps organizations maintain optimal
inventory levels, reduce costs, and
improve supply chain efficiency.
ADVANTAGES
AND
DISADVANTAGES
ADVANTAGES AND DISADVANTAGES
• ADVANTAGES :
• Informed Decision-Making: DSS provides
timely and relevant information to
decisionmakers, enabling them to make well-
informed choices based on accurate data and
analyses.
• Complex Problem Solving: DSS can handle
complex problems by employing sophisticated
ADVANTAGES AND DISADVANTAGES
models, algorithms, and simulations that may
be challenging to solve manually.
• Scenario Analysis: DSS allows users to
evaluate various scenarios and their potential
outcomes, helping decision-makers
understand the implications of different
choices.
• Collaboration: DSS facilitates collaboration
among decision-makers, enabling them to
ADVANTAGES AND DISADVANTAGES
share insights, analyses, and scenarios for
more effective group decisions.
• DISADVANTAGES :
• Complex Implementation: Developing and
implementing a DSS requires skilled
professionals, resources, and integration with
existing systems.
• Cost: Building and maintaining a DSS can incur
significant costs, including software
ADVANTAGES AND DISADVANTAGES
development, hardware, training, and ongoing
support.
• User Expertise: Effective use of DSS may require
users to have a certain level of technical and
analytical expertise, which could be a barrier for
some individuals.
UNIT - IV
MODELING AND
ANALYSIS
MODELING AND ANALYSIS
• SYLLABUS :
• Management Support Systems Modeling,
Structure of Mathematical Models for
Decision Support, Certainty, Uncertainty, and
Risk Management Support Systems,
Mathematical Programming Optimization,
Spreadsheet Model, Linear Programming,
Multiple Goals, Sensitivity Analysis, What-If
Analysis, and Goal Seeking, Decision Analysis
with Decision Tables and Decision Trees
MANAGEMENT SUPPORT
SYSTEMS MODELING
MANAGEMENT SUPPORT SYSTEMS
MODELING
• Factors in modeling a Management Support
System :
• Support from the top management
• Objectives and benefits clearly defined
• Identifying executives’ information needs
• Keeping lines of communication open
• System’s complexity hidden; interface kept
simple
• Maintaining consistency in the approach of
designing
• Designing a flexible system
MATHEMATICAL
PROGRAMMING
OPTIMIZATION
OPTIMIZATION
• Mathematical optimization (alternatively
spelled optimisation) or mathematical
programming is the selection of a best
MATHEMATICAL PROGRAMMING
element, with regard to some criterion,
from some set of available alternatives.
• It is generally divided into two subfields:
– discrete optimization and
– continuous optimization
OPTIMIZATION
• In the more general approach, an optimization
problem consists of maximizing or minimizing a
real function by systematically choosing input
MATHEMATICAL PROGRAMMING
values from within an allowed set and
computing the value of the function.
• An optimization problem with discrete variables
is known as a discrete optimization, in which an
object such as an integer, permutation or
graph must be found from a countable set.
OPTIMIZATION
• A problem with continuous variables is known as
a continuous optimization, in which optimal
arguments from a continuous set must be found.
MATHEMATICAL PROGRAMMING
They can include constrained problems and
multimodal problems.
• Given: a function f : A → R from some set A to the
real numbers
• Sought: an element x0 A such that f(x0) ≤ f(x) for
all x A ("minimization") or such that f(x0) ≥ f(x)
for all x A ("maximization").
MATHEMATICAL PROGRAMMING
OPTIMIZATION
• Such a formulation is called an optimization
problem or a mathematical programming
problem
• Many real-world and theoretical problems
may be modeled in this general framework.
SPREADSHEET MODEL
• Spreadsheet modelling is the creation of various
models using spreadsheet software like MS
Excel.
• The software is used to organise data and apply
formulas to understand the reasons for various
events.
• Models are also used to predict events in the
future.
SPREADSHEET MODEL
• Spreadsheets are very versatile as they allow you
to enter different data types and apply various
formulas to arrive at a desired outcome.
• They automatically calculate the values as per
the formula you have fed. They also allow you
to visualise the outcome as charts and graphs
• There are numerous advantages to creating a
model using spreadsheets.
– Models allow us to communicate with different
people easily.
SPREADSHEET MODEL
– They also enable us to clarify and test our
understanding of various occurrences in business.
• Spreadsheet modelling creates credibility and
accountability as everyone can see how the
formulas have been applied and build trust in
the outcome.
• These models simplify problems and help you
solve them.
SPREADSHEET MODEL
• These models are ideal for analysing data as
you can feed the formula and see the results
by just changing the input value.
• You can keep changing the values until you
get the outcome you desire.
• Features Of Spreadsheet Models:
• There are various spreadsheets that one can
use for modelling.
SPREADSHEET MODEL
• MS Excel, Google Sheets and Airtable are
some popular applications used in data
analysis.
• Almost all of them have similar features,
though there may be differences in how you
input data or get your results.
• Rows and columns in which you enter your
data are common to all these applications.
SPREADSHEET MODEL
• Some other features are also common to all
software programmes used in spreadsheet
modelling :
– Formulas And Functions
– Enabling Visualisation
– Format The Way You Want
• Formulas And Functions
• All spreadsheets allow you to create unique
formulas that will help you analyse the
SPREADSHEET MODEL
available data and help you get the desired
outcome.
• Some functions and formulas are already
available with the application.
• But you can also make a custom function and
have it displayed for everyone to see what
formula you have used.
• Experts use functions in a spreadsheet to
evaluate values.
SPREADSHEET MODEL
• Formulas help to represent the
relationship between two cells in the
sheet.
• Formulas include basic arithmetic like
addition, subtraction and multiplication.
Functions are represented by sum,
average, count, etc.
• Enabling Visualisation
SPREADSHEET MODEL
• Visualisation is very important in data analysis.
• It is not possible to show the tables and the
outcome to everyone.
• It is also difficult for most people to understand
what you have represented in the spreadsheets.
One of the most important features of
spreadsheet modelling is visualisation.
• You can show the results of your analysis using
various visual aids like graphs and charts.
SPREADSHEET MODEL
• It is possible to use various styles when
presenting your graphs, like bar graphs, pie
charts, etc. Spreadsheets also enable you to
add different colours to make the
presentation more attractive and clear.
• Format The Way You Want
• The biggest advantage of using applications
like MS Excel for spreadsheet modelling is
that they allow you to format the way you
want.
SPREADSHEET MODEL
• You can separate information and create
headers.
• It is also possible to merge cells and make
them bigger to accommodate large amounts
of data without disturbing the other cells.
• The other advantage of spreadsheets is that
you can use different colours for different
cells to highlight any important information.
SPREADSHEET MODEL
• You can also apply conditional formatting in
individual cells to make them appear
different.
• It helps you locate critical information without
searching the whole sheet.
SPREADSHEET MODEL
• Elements Of A Spreadsheet Model:
• A spreadsheet model has different elements that
help you display the data and make the analysis
that you desire:
1. Input Variables
2. Output Variables
3. Model Requirements
4. Data Tables
SPREADSHEET MODEL
5. Data Labels
SPREADSHEET MODEL
1. Input Variables –
• These are numerals that the analyst
enters in the spreadsheet to arrive at an
outcome or response.
• The input variables will have an impact
on the output.
• Output Variables –
• Output variables are the result of the
operation in a spreadsheet.
• They help to know what will happen if there
are changes to the input.
SPREADSHEET MODEL
• These elements in spreadsheet modelling
help companies predict the result of changes
in various metrics.
SPREADSHEET MODEL
3. Model Requirements –
These are the requirements of a spreadsheet
model that are necessary for generating the
desired outcome.
4. Data Tables
• These represent the changes that a firm wants
to track.
• It could be the sales in the coming few years
or the number of customers added in a certain
period in the future.
SPREADSHEET MODEL
SPREADSHEET MODEL
5. Data Labels
• Data labels are names that the user gives to
various pieces of data to make it easy to
identify a data series in the spreadsheet.
• Best Practices For Building Spreadsheet
Models:
• Consistency
• Flexibility
• Transparency
• Accuracy
SPREADSHEET MODEL
• Consistency
• Consistency is very important when you
create a model.
• Using the same formatting style for all your
models is always better.
• It makes your models easy to understand for
others.
• Others can also add or delete information
easily if the formatting is consistent.
SPREADSHEET MODEL
• Flexibility
• One of the attributes that are important for
spreadsheet modelling is flexibility.
• Making a flexible model allows us to change
the formulas and see how they impact the
outcome.
• One of the ways to improve flexibility is by
only entering positive numbers so that it fits
in any formula.
SPREADSHEET MODEL
• Transparency
• A transparent model is one where there is
only one calculation in one spreadsheet.
• It is better for an easy understanding of the
information and the outcome.
• It is always better to have different
spreadsheets for different calculations.
• Accuracy
SPREADSHEET MODEL
• To get an accurate model is essential to feed
only correct data.
• If there are any errors in the data, it is better
to remove them to avoid more inaccuracies in
the model.
• One of the ways to avoid errors is to create a
filter that will show unique values in your
spreadsheet.
• Popular Spreadsheet Applications
SPREADSHEET MODEL
• MS Excel
• MS Excel, by far, is the most popular
spreadsheet application available today.
• It is used very commonly for various functions
and is a favourite among data analysts.
• Excel offers various features, from basic
mathematical calculations to highly complex
automation.
SPREADSHEET MODEL
• It is available as a desktop application or
webbased software.
• People prefer this for spreadsheet modelling
due to its versatility and ability to embed
spreadsheets on the website.
• Google Sheets
• Google sheets is an application that comes free
with all personal and business Gmail accounts.
SPREADSHEET MODEL
• It easily integrates with other programmes like
Google Analytics, Google Data Studio and
Google Forms.
• This makes importing and exporting data very
easy.
• One of the things that business owners like about
Google Sheets is its cloud and web-based
accessibility anywhere.
LINEAR PROGRAMMING
LINEAR PROGRAMMING
• Linear programming is a mathematical
concept that is used to find the optimal
solution of the linear function.
• This method uses simple assumptions for
optimizing the given function.
• Linear Programming has a huge real-world
application and it is used to solve various
types of problems.
LINEAR PROGRAMMING
• Linear programming is used in various
industries such as shipping industries,
manufacturing industries, transportation
industries, telecommunications, and others.
LINEAR PROGRAMMING
• Term “linear programming” consists of
two words linear and programming,
the word linear tells the relation
between various types of variables of
degree one used in a problem and the
word programming tells us the step-by-
step procedure to solve these
problems.
LINEAR PROGRAMMING
• What is Linear Programming?
• Linear programming or Linear
optimization is a technique that helps us
to find the optimum solution for a given
problem, an optimum solution is a
solution that is the best possible
outcome of a given particular problem.
• The situation that requires a search for
the best values of the variables subject
LINEAR PROGRAMMING
to certain constraints is where we use
linear programming problems.
• These situations cannot be handled by
the usual calculus and numerical
techniques.
• Linear Programming Definition
• Linear programming is the technique
used for optimizing a particular scenario.
LINEAR PROGRAMMING
• Using linear programming provides us
with the best possible outcome in a
given situation.
• It uses all the available resources in a
manner such that they produce the
optimum result.
• Components of Linear Programming
• The basic components of a linear programming(LP)
problem are:
LINEAR PROGRAMMING
• Decision Variables: Variables you want to determine
to achieve the optimal solution.
• Objective Function: Mathematical equation that
represents the goal you want to achieve
• Constraints: Limitations or restrictions that your
decision variables must follow.
• Non-Negativity Restrictions: In some real-world
scenarios, decision variables cannot be negative
LINEAR PROGRAMMING
• Objective Function: Z = ax + by
• Constraints: cx + dy ≥ e, px + qy ≤ r
• Non-Negative restrictions: x ≥ 0, y ≥ 0
• In the above condition x, and y are the
decision variables.
• Additional Characteristics of Linear
Programming
LINEAR PROGRAMMING
• Finiteness: The number of decision variables
and constraints in an LP problem are finite.
• Linearity: The objective function and all
constraints must be linear functions of the
decision variables. It means the degree of
variables should be one.
• Linear Programming Examples
• We can understand the situations in which
Linear programming is applied with the help
of the example discussed below,
LINEAR PROGRAMMING
• Suppose a delivery man has to deliver 8
packets in a day to the different locations of a
city.
• He has to pick all the packets from A and has
to deliver them to points P, Q, R, S, T, U, V,
and W.
• The distance between them is indicated using
the lines as shown in the image below.
LINEAR PROGRAMMING
• The shortest path followed by the delivery
man is calculated using the concept of Linear
Programming.
• Linear Programming Problems
LINEAR PROGRAMMING
• Linear Programming Problems (LPP) involve
optimizing a linear function to find the optimal
value solution for the function. The optimal value
can be either the maximum value or the
minimum value.
• In LPP, the linear functions are called objective
functions. An objective function can have
multiple variables, which are subjected to
conditions and have to satisfy the linear
constraints.
• Types of Linear Programming Problems
LINEAR PROGRAMMING
• There are many different linear programming
problems(LPP) but we will deal with three major
linear programming problems in this article.
• Manufacturing Problems
• Manufacturing problems are a problem that
deals with the number of units that should be
produced or sold to maximize profits when each
product requires fixed manpower, machine
hours, and raw materials.
• Diet Problems
LINEAR PROGRAMMING
• It is used to calculate the number of different
kinds of constituents to be included in the diet to
get the minimum cost, subject to the availability
of food and their prices.
• Transportation Problems
• It is used to determine the transportation
schedule to find the cheapest way of transporting
a product from plants /factories situated at
different locations to different markets.
LINEAR PROGRAMMING
• How to Solve Linear Programming
Problems?
• Before solving the linear programming
problems first we have to formulate the
problems according to the standard
parameters.
• The steps for solving linear programming
problems are,
LINEAR PROGRAMMING
• Step 1: Mark the decision variables in the
problem.
• Step 2: Build the objective function of the
problem and check if the function needs to be
minimized or maximized.
• Step 3: Write down all the constraints of the
linear problems.
• Step 4: Ensure non-negative restrictions of the
decision variables.
LINEAR PROGRAMMING
• Step 5: Now solve the linear programming
problem using any method generally we use
either the simplex or graphical method.
• Linear Programming Methods
• We use various methods for solving linear
programming problems. The two most
common methods used are,
• Simplex Method
• Graphical Method
• Linear Programming Applications
LINEAR PROGRAMMING
• Linear Programming has applications in various
fields.
• It is used to find the minimum cost of a process
when all the constraints of the problems are
given.
• It is used to optimize the transportation cost of
the vehicle, etc.
• Various applications of Linear Programming are
• Engineering Industries
LINEAR PROGRAMMING
• Engineering Industries use linear
programming to solve design and
manufacturing problems and to get the
maximum output from a given condition.
• Manufacturing Industries
• Manufacturing Industries use linear
programming to maximize the profit of the
companies and to reduce the manufacturing
cost.
• Energy Industries
LINEAR PROGRAMMING
• Energy companies use linear programming to
optimize their production output.
• Transportation Industries
• Linear programming is also used in
transportation industries to find the path to
minimize the cost of transportation.
SENSITIVITY ANALYSIS
SENSITIVITY ANALYSIS
• Sensitivity analysis is a financial modelling tool
used to analyse how different values of an
independent variable affect a particular
dependent variable under a certain set of
assumptions.
• It studies how various sources of uncertainty
contribute to the forecast’s overall uncertainty
by posing ‘what if’ questions.
• Sensitivity analysis is used within specific
boundaries that depend on one or more input
variables, and is implemented in a wide range of
fields.
SENSITIVITY ANALYSIS
• How Sensitivity Analysis works
• Most commonly used by financial analysts
and economists, it is also known as what-if or
simulation analysis.
SENSITIVITY ANALYSIS
• It can be used to ascertain how interest rates
affect bond prices and in making predictions
about the share price of publicly traded
companies.
• The technique allows analysts to establish
which variables are more critical than others
in affecting a decision.
• Thus, it offers investors insight into how
different variables can impact upon their
potential investment returns.
• The analyst will look at how the variables
move, as well as how the target is affected by
the input variable.
SENSITIVITY ANALYSIS
• Sensitivity analysis allows for forecasting using
historical data, paving the way for important
SENSITIVITY ANALYSIS
decisions to be made about businesses, the
economy and making investments
• An Example of Sensitivity Analysis
• X is the head of sales for a small garden centre
that sells everything from plants and garden
supplies to home products, garden furniture and
even pet essentials.
• He knows that revenue increases every summer
as more customers visit in the warmer weather
and focus on upkeep for their gardens.
• But this year he wants to find out exactly how
much sales will rise in accordance with higher
percentages of customer traffic.
SENSITIVITY ANALYSIS
• Sensitivity Analysis advantages
• The advantages of sensitivity analysis are
numerous. Because it’s an in-depth study of
all the variables, the predictions are far more
reliable.
SENSITIVITY ANALYSIS
• It allows decision-makers to see exactly where
they can make improvements and enable
people to make sound decisions about
companies, the economy or their
investments.
SENSITIVITY ANALYSIS
• Sensitivity analysis is also fairly simple to
understand.
• The numerical outcomes do not favour any
particular variables.
SENSITIVITY ANALYSIS
• Sensitivity Analysis disadvantages
• There are some disadvantages to sensitivity
analysis to consider.
• By using historical data to forecast the effect of
variables on outcomes, there is room for error.
• For example, Barry’s garden centre may not sell
as many BBQs this year for reasons not added
to the sensitivity analysis, such as cheaper
models offered by a competitor at a special
discount.
WHAT IF ANALYSIS
WHAT IF ANALYSIS
• What-if analysis is one way of spreadsheet
modelling that is used to find the effect of
certain values on the result.
• By changing certain values in the spreadsheet,
you can know what change it will have in the
outcome.
• For example, if you are calculating the profit
margin of a company after entering the income
WHAT IF ANALYSIS
and expense details, you can easily see how to
achieve the target profit margin.
• You can do this by changing the values in
different rows that represent each item of
income and expenditure.
• As the sales of products are dependent on
various external factors, the best way to
increase profit margins is to reduce expenses.
WHAT IF ANALYSIS
• You can start changing the values in each
expense head and see what changes it will
bring to your profits.
• If you have a target profit margin in mind, you
can change the values of expenses and find
out how much you can spend the most.
WHAT IF ANALYSIS
• You can keep the sales figures as an average
of the past few months to get the actual
value.
• This type of spreadsheet modelling is known
as the “what-if analysis”.
GOAL SEEK
• In the “what if analysis” method, it will take a
few tries to arrive at the correct values.
• You will have to keep changing each expense
item to see what will give you the desired
result.
GOAL SEEK
• But if you are sure about which expense can
be reduced, then it is best to use the goal-
seek method for spreadsheet modelling.
• In this method, the idea is to find out the
value in one cell that will give us the result we
seek.
GOAL SEEK
• Suppose we want to reduce salary expenses
to achieve a particular profit margin, you can
do so easily.
• To achieve this, we need to enter the right
inputs in the goal-seek dialogue box
• We must give the location of the cell that
contains the formula that needs solving.
GOAL SEEK
• We must also specify the cell containing our
desired profit margin.
• The other thing that needs to be mentioned is
the cell that contains the number that can be
changed.
• Once this is done, you must enter the desired
profit margin in the To Value text box.
GOAL SEEK
• This is an excellent spreadsheet modelling for
finding out the target value for achieving a
specific result.
DECISION ANALYSIS WITH
DECISION TABLES AND
DECISION TREES
TABLES AND DECISION TREES
1. Decision Table:
• Decision Table is just a tabular representation
of all conditions and actions.
DECISION ANALYSIS WITH DECISION
• Decision Table are always used whenever the
processing logic is very complicated and
involves multiple conditions.
• The main components used for the formation
of the Data Table are Conditions Stubs, Action
Stubs, and rules.
TABLES AND DECISION TREES
• Types of decision tables:
• Extended entry table
DECISION ANALYSIS WITH DECISION
• Limited entry table
TABLES AND DECISION TREES
• Benefits:
• Visualization of Cause and effect
relationships in the table.
• Easy to understand
• In the case of a complex table, it can be
readily broken down into simpler tables.
DECISION ANALYSIS WITH DECISION
• Tables are formatted consistently.
TABLES AND DECISION TREES
• Suggestions of possible actions need to be
taken from the summarized outcomes of a
situation.
• In these tables, semi-standardized languages
might be used.
• Table users are not necessarily know how to
use a computer.
DECISION ANALYSIS WITH DECISION
TABLES AND DECISION TREES
• Drawbacks:
• Decision tables are not well suited to
largescale applications. There is a
requirement of splitting huge tables into
smaller ones to eliminate redundancy.
• The complete sequence of actions is not
reflected in the decision tables.
• A partial solution is presented.
DECISION ANALYSIS WITH DECISION
TABLES AND DECISION TREES
• 2. Decision Tree: A decision tree is a graph
that always uses a branching method in order
to demonstrate all the possible outcomes of
any decision. Decision Trees are graphical and
show a better representation of decision
outcomes. It consists of three nodes namely
Decision Nodes, Chance Nodes, and Terminal
Nodes.
DECISION ANALYSIS WITH DECISION
TABLES AND DECISION TREES
• Types of the decision tree:
• Categorical variable decision tree
• Continuous variable decision tree
TABLES AND DECISION TREES
• Benefits:
DECISION ANALYSIS WITH DECISION
• A decision tree is simple to comprehend
and use.
• New scenarios are simple to add.
• Can be combined with other
decisionmaking methods.
TABLES AND DECISION TREES
• Handling of both numerical and
categorial variables
DECISION ANALYSIS WITH DECISION
• The classification does not require many
computations.
• Useful in analyzing and solving various
business problems.
TABLES AND DECISION TREES
• Drawbacks:
• They are inherently unstable, which means
that a slight change in the data can have a
result in a change in the structure of the
DECISION ANALYSIS WITH DECISION
optimal decision tree, and they are frequently
wrong.
• These are less suitable for estimation tasks
where the outcome required is the value of a
continuous variable.
TABLES AND DECISION TREES
• The alternative options perform better with
the same data. A random forest of decision
trees can be used as a replacement but it is
DECISION ANALYSIS WITH DECISION
not as straightforward to comprehend as a
single decision tree.
• Calculations can become quite complicated,
especially when several values are uncertain
and/or multiple outcomes are related.
TABLES AND DECISION TREES
• Difference between Decision Table and
Decision Tree:
S. No. Decision Table Decision Tree
DECISION ANALYSIS WITH DECISION
Decision Tables are a tabular Decision Trees are a graphical
1. representation of conditions and representation of every possible
actions. outcome of a decision.
We can derive a decision table from the We can not derive a decision tree
2.
decision tree. from the decision table.