Decision Support Systems

and Business Intelligence

Chapter Two - Decision Making,

Systems, Modeling, and Support
Dr Yasmin Sakka
 Decision Making: Introduction and
Definitions

• Decision making
The action of selecting among
alternatives
 Decision Making: Introduction and
Definitions
• Characteristics of decision making
– Groupthink
– Decision makers are interested in evaluating what‐if scenarios
– Experimentation with the real system may result in failure
– Experimentation with the real system is possible only for one set
of conditions at a time and can be disastrous
– Changes in the decision making environment may occur
continuously, leading to invalidating assumptions about the
situation
Decision Making: Introduction and Definitions

• Characteristics of decision making

• Changes in the decision making
environment may affect decision
quality by imposing time pressure on
the decision maker
• Collecting information and analyzing
a problem takes time and can be
expensive. It is difficult to determine
when to stop and make a decision
• There may not be sufficient
information to make an
intelligent decision
• Information overload
Phases of the Decision‐Making Process
 Phases of the Decision‐Making Process

• Intelligence phase
The initial phase of problem definition in
decision making
• Design phase
The second decision‐making phase, which
involves finding possible alternatives in
decision making and assessing their
contributions
 Phases of the Decision‐Making Process
• Choice phase
The third phase in decision making, in which
an alternative is selected
• Implementation phase
The fourth decision‐making phase, involving
actually putting a recommended solution to
work
 Decision Making: The Intelligence Phase
1. Problem (or opportunity) identification: some issues that
may arise during data collection
1. Data are not available
2. Obtaining data may be expensive
3. Data may not be accurate or precise enough
4. Data estimation is often subjective
5. Data may be insecure
6. Important data that influence the results may be Iinformation overload
7. Outcomes (or results) may occur over an extended period
8. If future data is not consistent with historical data, the nature of the change has to be
predicted and included in the analysis
 Decision Making: The Intelligence Phase
2. Problem classification
The conceptualization of a problem in an attempt to
place it in a definable category, possibly leading to a
standard solution approach
3. Problem decomposition
Dividing complex problems into simpler subproblems
may help in solving the complex problem
4. Problem ownership
The jurisdiction (authority) to solve a prob
lem
 Decision Making: The Design Phase
• The design phase involves finding or developing and
analyzing possible courses of action
– Understanding the problem
– Testing solutions for feasibility
1. A model of the decision‐making problem is construced,
tested, and validatedt
– Decision variables
– Principle of choice
 Decision Making: The Design Phase
2. Decision variables
A variable in a model that can be changed and
manipulated by the decision maker. Decision variables
correspond to the decisions to be made, such as quantity
to produce, amounts of resources to allocate, and so on
• Principle of choice
The criterion for making a choice among
alternatives
 Decision Making: The Design Phase
3. Developing (generating) alternatives
– In optimization models the alternatives may be generated
automatically by the model
– In most MSS situations it is necessary to generate alternatives
manually (a lengthy, costly process); issues such as when to stop
generating alternatives are very important
– The search for alternatives usually occurs after the criteria for
evaluating the alternatives are determined
– The outcome of every proposed alternative must be established
 Decision Making: The Design Phase
4. Measuring outcomes
– The value of an alternative is evaluated in terms of
goal attainment
• Risk
– One important task of a decision maker is to attribute
a level of risk to the outcome associated with each
potential alternative being considered
 Decision Making: The Choice Phase

1. Sensitivity Analysis
• A study of the effect of a change in one or more input variables
on a proposed solution
• What‐if analysis
• A process that involves asking a computer what the effect of changing
some of the input data or parameters would be
Decision Making: The Implementation Phase

• Generic implementation issues important in

dealing with MSS include:
1. Resistance to change
2. Degree of support of top management
3. User training
DSS Support
 How Decisions Are Supported
• Support for the intelligence phase
– The ability to scan external and internal information
sources for opportunities and problems and to
interpret what the scanning discovers
• Web tools and sources are extremely useful for
environmental scanning
• Web browsers provide useful front ends for a variety of tools
(OLAP, data mining, data warehouses)
• Internal data sources may be accessible via a corporate
intranet
• External sources are many and varied
 How Decisions Are Supported
• Support for the design phase
– The generation of alternatives for complex problems
requires expertise that can be provided only by a
human, brainstorming software, or an ES
 How Decisions Are Supported

• Support for the choice phase

– DSS can support the choice phase through what‐if and
goal‐ seeking analyses
– Different scenarios can be tested for the selected option to
reinforce the final decision
– KMS helps identify similar past experiences
– CRM, ERP, and SCM systems are used to test the impacts of
decisions in establishing their value, leading to an intelligent
choice
– An ES can be used to assess the desirability of certain solutions
and to recommend an appropriate solution
– A GSS can provide support to lead to consensus in a group
 How Decisions Are Supported
• Support for the implementation phase
– DSS can be used in implementation activities such as
decision communication, explanation, and justification

– DSS benefits are partly due to the vividness and detail

of analyses and reports
 Specific uses for DSSs in business

• Medicine: When a DSS is used in medicine, it is known as a clinical DSS. The technology
can be used in a variety of ways, such as maintaining research information about
chemotherapy protocols, preventive and follow-up care, and monitoring medication
orders. DSSs are also used with medical diagnosis software.
• Weather forecasting: Some states have used DSSs to provide information about
potential hazards, such as floods. The system includes real-time weather conditions and
may include information, both current and historical, about floodplain boundaries and
county flood data.
• Real estate: Real estate companies often use DSSs to manage data on comparable home
prices and acreage.
• Education: Universities and colleges rely on DSSs to know how many students are
currently enrolled. This helps them predict how many students will register for particular
courses or whether the student population is sufficient to meet the university’s costs.
 DSS Modeling

• Key element in DSS

• Many classes of models
• Specialized techniques for each model
• Allows for rapid examination of alternative solutions
• Multiple models often included in a DSS
• Model is a representation of an actual system.
• Models embody system characteristics that are important to the model’s users.
• At the same time, models simplify reality by eliminating other characteristics that are not
important for their purpose.
• The central idea of a model is that important relationships that apply to the system being
modeled also apply to the model.
 DSS Modeling
• The benefits of models
– Model manipulation is much easier than
manipulating a real system
– Models enable the compression of time
– The cost of modeling analysis is much
lower
– The cost of making mistakes during a trial‐and‐
error experiment is much lower when models
are used than with real systems
 DSS Modeling

– With modeling, a manager can estimate the risks

resulting from specific actions within the uncertainty of
the business environment
– Mathematical models enable the analysis of a very large
number of possible solutions
– Models enhance and reinforce learning and training
– Models and solution methods are readily available on
the Web
 DSS Models

• Algorithm-based models
• Statistic-based models
• Linear programming models
• Graphical models
• Quantitative models
• Qualitative models
• Simulation models
 Modeling and Decision Making -
Under Certainty, Uncertainty, and Risk
• Certainty
• Assume complete knowledge
• All potential outcomes are known
• May yield optimal solution
• Uncertainty
• Several outcomes for each decision
• Probability of each outcome is unknown
• Knowledge would lead to less uncertainty
• Risk analysis (probabilistic decision making)
• Probability of each of several outcomes occurring
• Level of uncertainty => Risk (expected value)
 Modeling and Decision Making -
Under Certainty, Uncertainty, and Risk
The Zones of Decision Making
 Decision Tables

• Decision tables are a convenient way to organize information in a systematic

manner. It can be done in a spreadsheet and thus looks like a table.
• Multiple criteria decision analysis
• Features include:
• Decision variables (alternatives)
• Uncontrollable variables
• Result variables
• Applies principles of certainty, uncertainty, and risk
 Example

• An investment company is considering investing in one of three alternatives:

• bonds, stocks, or certificates of deposit (CDs). The company is interested in one goal: maximizing the
yield on the investment after one year.
• If it were interested in other goals, such as safety or liquidity, the problem would be classified as
one of multi-criteria decision analysis.
• The yield depends on the state of the economy sometime in the future (called the state of nature),
which can be in solid growth, stagnation, or inflation. Experts estimated the following annual yields:
If there is solid growth in the economy, bonds will yield 12%, stocks 15%, and time deposits
6.5%.
 If stagnation prevails, bonds will yield 6%, stocks 3%, and time deposits 6.5%.
 If inflation prevails, bonds will yield 3%, stocks will bring a loss of 2%, and time deposits will
yield 6.5%.
 Treatment the risk
 The most common method for solving this risk analysis problem is to select the
alternative with the greatest expected value.
• Assume that the experts estimate the chance of solid growth at 50%, the chance of
stagnation at 30%, and the chance of inflation at 20%.
• The decision table is then rewritten with the known probabilities (see next table).
• An expected value is computed by multiplying the results (outcomes) by their
respective probabilities and adding them. For example, investing in bonds yields an
expected return of 12(0.5)+6(0.3)+3(0.2)=8.4%
 Decision Tree

• It is a schematic presentation of alternatives, their potential consequences with

their probabilities and payoffs. It is usually used to describe several interrelated
decisions over several years.
• Graphical representation of relationships
• Multiple criteria approach
• Demonstrates complex relationships
 Classification

• Classification: classifies data (constructs a model) based on the training

set and the values (class labels) in a classifying attribute and uses it in
classifying new data.
• Given a database D={t1,t2,…,tn} and a set of classes C={C1,…,Cm}, the
Classification Problem is to actually divides D into equivalence classes.
Training Dataset
Output: A Decision Tree for
”“buys_computer
 Sensitivity, What-if, and Goal Seeking Analysis

• Sensitivity
• Allows for adaptability and flexibility
• Eliminates or reduces variables
• Can be automatic or trial and error
• What-if
• Assesses solutions based on changes in variables or assumptions
• Goal seeking
• Backwards approach, starts with goal
• Determines values of inputs needed to achieve goal
 Structure of Mathematical Models
for Decision Support
• Link decision variables, uncontrollable variables, parameters, and result variables
together
• Decision variables describe alternative choices.
• Uncontrollable variables are outside decision-maker’s control.
• Result variables are dependent on chosen solution and uncontrollable variables.
The Structure of a Mathematical Model
 The components of a quantitative model are linked
together by mathematical (algebraic) expressions—
equations or inequalities.
 Example – Profit -

whereP= profit, R= revenue, and C= cost

 Example - Simple Present-Value -

whereP= present value, F= future cash-flow, i= interest-rate,

and n = number of period (years)
 Decision Modeling with Spreadsheets
• Spreadsheet
• Most popular end-user modeling tool
• Flexible and easy to use
• Powerful functions (add-in functions)
• Programmability (via macros)
• What-if analysis and goal seeking
• Simple database management
• Seamless integration of model and data
• Incorporates both static and dynamic models
• Examples: Microsoft Excel, Lotus 1-2-3
Excel spreadsheet - static model example: (Simple
loan calculation of monthly payments)

F  P (1  i ) n
 i (1  i ) n 
A  P 
 (1  i ) n
 1 
 Multiple Goals, Sensitivity Analysis, What-If
Analysis, and Goal Seeking
• What-if analysis
• Assesses solutions based on changes in variables or
assumptions (scenario analysis)
• What if we change our capacity at the milling station by 40%
[what would be the impact]
• Goal seeking
• Backwards approach, starts with the goal and determines
values of inputs needed
• Example is break-even point determination
• In-order to break even (profit = 0), how many products do
we have to sell each month
 Practical Example

• You need a loan to buy a new car.

• You know how much money you want to borrow,
how long of a period of time you want to take to
pay off the loan (the term), and
what payment you can afford to make each
month.
• But what you need to know is what interest rate
you need to qualify for to make the payment $400
per month. In the image below, you can see that if
you didn’t have interest and just divided this
$20,000 into 60 monthly payments, you would pay
$333.33 per month. The what-if analysis tool will
allow you to easily calculate the interest rate.
 Example

• To insert a payment function:

• Select the Formula tab.
• Click the Insert Function command. A
dialog box appears.
• Select PMT.
• Click OK. A dialog box appears.
• Insert your cursor in the first field. A
description of the needed information
appears at the bottom of the dialog box.
 What-If Analysis tools

• What-If Analysis tools

• There are three What-If analysis tools that you can use. To access these, select the
Data tab and locate the What-If Analysis command. If you click this command, a
menu with three options appears.
• Goal seek is useful if you know the needed result but need to find the input value
that will give you the desired result. In this example, we know the desired result
(a $400 monthly payment) and are seeking the input value (the interest rate).
 Goal Seek

• Select Goal Seek. A small dialog box appears.

• Select the cell that you want to set to a specific value. In this example, we want to
set B5, the Payment cell.
• Insert the cursor in the next field.
• Enter a value in the value field. In this example, type -$400. Since we’re making a
payment that will be subtracted from our loan amount, we have to enter the payment
as a negative number.
Then, click OK again. The interest rate appears in the cell. This indicates that a 7%
interest rate will give us a $400 a month payment on a $20,000 loan that is paid off
over five years, or 60 months.
 Other types of what-if analysis
• For more advanced projects, you may want to consider the other types of what-if
analysis: scenarios and data tables. Rather than start from the desired result and
working backward like with Goal Seek, you can use these options to test multiple
values and see how the results change.

• Scenarios let you substitute values for multiple cells (up to 32) at the same time.
You can create as many scenarios as you want and then compare them without
changing the values manually. In the example below, each scenario contains a term
and an interest rate. When each scenario is selected, it will replace the values in
the spreadsheet with its own values, and the result will be recalculated.
Scenarios and Data Tables
 Scenarios and Data Tables
• Data tables allow you to take one or two variables in a formula and replace them
with as many different values as you want, then view the results in a table. This
option is especially powerful because it shows multiple results at the same time,
unlike scenarios or Goal Seek. In the example below, we can view 24 possible
results for a car loan.
 Scenarios and Data Tables
• Data tables allow you to take one or two variables in a formula and replace them
with as many different values as you want, then view the results in a table. This
option is especially powerful because it shows multiple results at the same time,
unlike scenarios or Goal Seek. In the example below, we can view 24 possible
results for a car loan.