DECISION SUPPORT SYSTEMS

(DSS)
Dissecting DSS into its main
concepts

Building successful DSS

requires a through
understanding of these
concepts
DECISION MAKING PROCESS
 DSS by definition help people make
decisions.
 Must fit into the way human work
 understand human decision making process
to develop DSS….specifically a managers
WHAT IS A DECISION
 Reasoned choice among alternatives.
 Decisions: personal, business
 Decision making is process of choosing among
two or more alternative courses of action for
the purpose of attaining one or more goals.
BASIC TERMINOLOGY IN
DECISION MAKING
 Information
 Alternatives
 Criteria
 Goals
 Value
 Preferences
 Decision Quality
 Acceptance
RATIONAL PERSPECTIVES ON
DECISION MAKING
 The Classical Model of Decision Making

• obtain complete
. . . and end up with
When faced with a and perfect information
a decision that best
decision situation, • eliminate uncertainty
serves the interests
managers should . . . • evaluate everything
of the organization.
rationally and logically

Figure 9.2
Copyright © by Houghton Mifflin Company. All rights
reserved. 9–5
STEPS IN THE RATIONAL
DECISION-MAKING PROCESS
Step Detail Example

1. Recognizing and Some stimulus indicates that a A plant manager sees that
defining the decision decision must be made. The employee turnover has in-
situation stimulus may be positive or creased by 5 percent.
negative.

2. Identifying alterna- Both obvious and creative The plant manager can in-
tives alternatives are desired. In crease wages, increase bene-
general, the more important fits, or change hiring stan-
the decision, the more alterna- dards.
tives should be considered.

3. Evaluating alterna- Each alternative is evaluated Increasing benefits may not be

tives to determine its feasibility, its feasible. Increasing wages and
satisfactoriness, and its changing hiring standards may
consequences. satisfy all conditions.

Table 9.1a
Copyright © by Houghton Mifflin Company. All rights
reserved. 9–6
 STEPS IN THE RATIONAL
DECISION-MAKING PROCESS (CONT’D)

Step Detail Example

4. Selecting the best Consider all situational factors, Changing hiring standards will take
alternative and choose the alternative that an extended period of time to cut
best fits the manager’s turnover, so increase wages.
situation.

5. Implementing the The chosen alternative is The plant manager may need
chosen alternative implemented into the permission from corporate
organizational system. headquarters. The human resource
department establishes a new wage
structure.

6. Following up and At some time in the future, the The plant manager notes that, six
evaluating the manager should ascertain the months later, turnover has dropped
results extent to which the alternative to its previous level.
chosen in step 4 and
implemented in step 5 has
worked.

Table 9.1b
Copyright © by Houghton Mifflin Company. All rights
reserved. 9–7
EVALUATING ALTERNATIVES IN THE
DECISION-MAKING PROCESS

Are the alternative’s

Is the alternative Is the alternative Retain for further
Yes Yes consequences Yes
feasible? satisfactory? consideration
affordable?

No No No

Eliminate from Eliminate from Eliminate from

consideration consideration consideration

Figure 9.3
Copyright © by Houghton Mifflin Company. All rights
reserved. 9–8
BEHAVIORAL ASPECTS OF
DECISION MAKING
 The Administrative Model of Decision Making

• use incomplete and

. . . and end up with a
When faced with a imperfect information
decision that may or may
decision situation • are constrained by
not serve the interests
managers actually… bounded rationality
of the organization.
• tend to satisfice

Figure 9.4
Copyright © by Houghton Mifflin Company. All rights
reserved. 9–9
BEHAVIORAL ASPECTS OF
DECISION MAKING (CONT’D)
 Bounded Rationality
 The concept that decision makers are limited by their
values and unconscious reflexes, skills, and habits.
 Satisficing
 The tendency to search for alternatives only until one
is found that meets some minimum standard of
sufficiency to resolve the problem.
 Coalition
A political force in decision making which consists of an
informal alliance of individuals or groups formed to
achieve a goal.

Copyright © by Houghton Mifflin Company. All rights

reserved. 9–10
BEHAVIORAL ASPECTS OF
DECISION MAKING (CONT’D)
 Intuition
 An innate belief about something without conscious
consideration.
 Escalation of Commitment
A decision maker is staying with a decision even when
it appears to be wrong.
 Risk Propensity
 The extent to which a decision maker
is willing to gamble when making
a decision.

Copyright © by Houghton Mifflin Company. All rights

reserved. 9–11
2-9: BOUNDED RATIONALITY
 Simon argued that people don’t always
optimize because it is often impractical to
consider all possible solutions to a problem.
 He notes that we often “simplify reality” by
looking for a solution that is acceptable, a
strategy he called satisficing.
 When people make rational decisions that
are bounded by often uncontrollable
constraints, he notes that they are operating
inside bounded reality.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 12
 OPTIMIZING VERSUS SATISFICING

Optimizing strategies Satisficing strategies

search here search here

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 13
2-8: RATIONAL DECISION MAKING
 Many decision strategies (next slide) attempt to
find optimal solutions.
 In many circles, this is considered to be rational
behavior.
 It is not always possible to optimize. Some
problems have only qualitative solutions. Others
may be quantitative but have multiple objectives
at odds with others.
 In such situations, rational behavior would be to
choose a “good” solution.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 14
MODELING AND ANALYSIS
STRATEGIES
Satisficing strategies: Optimizing strategies:
Simulation Linear programming
Forecasting Goal programming
“What if” analysis Simple queuing models
Markov analysis Investment models
Complex queuing Inventory models
methods Transportation models
Environmental
impact analysis

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 15
BEHAVIORAL ASPECTS OF
DECISION MAKING (CONT’D)
 Ethics and Decision Making
 Individualethics (personal beliefs about right and
wrong behavior) combine with the organization’s ethics
to create managerial ethics.
 Components of managerial ethics:
 Relationships of the firm to employees
 Employees to the firm
 The firm to other economic agents

Copyright © by Houghton Mifflin Company. All rights

reserved. 9–16
DECISION MAKING AND
PROBLEM SOLVING
 A problem occurs when a system
 does not meet its established goals
 does not yield the predicted results, or
 does not work as planned
 Problem is the difference between the desired
and actual outcome
 Problem solving also involves identification of
new opportunities
DECISION MAKING AND
PROBLEM SOLVING
 Are problem solving and decision making
different? Or, are they the same thing?
 Consider phases of the decision process
Phase (1) Intelligence
Phase (2) Design
Phase (3) Choice, and
Phase (4) Implementation & Monitoring
 (1)-(4): problem solving; (3): decision making
 (1)-(3): decision making; (4): problem solving
 decision making  problem solving
DECISION MAKING AS A COMPONENT
OF PROBLEM SOLVING

How Decision Making Relates to Problem Solving

MANAGERIAL DECISION MAKING
 Management is a process by which organizational
goals are achieved by using resources
 Inputs:resources
 Output: attainment of goals
 Measure of success: outputs / inputs
 Management  Decision Making
 Decision making: selecting the best solution from
two or more alternatives
MANAGERIAL DECISION MAKING
 Managerial decision making is synonymous with the
entire management process - Simon (1977)
 Managerial decision making is the process of
making a conscious choice between two or more
rational alternatives in order to select the one
that will produce the most desirable
consequences(benefits) relative to unwanted
consequences (costs).
 e.g., Planning
 What
should be done? When? Where? Why? How? By
whom?
MINTZBERG'S 10 MANAGERIAL
ROLES
Interpersonal
1. Figurehead
2. Leader
3. Liaison Decisional
7. Entrepreneur
Informational 8. Disturbance handler
9. Resource allocator
4. Monitor
10. Negotiator
5. Disseminator
6. Spokesperson
MANAGEMENT PROBLEMS
 Most management problems for which decisions are sought
can be represented by three standard elements – objectives,
decision variables, and constraints.
 Objective
 Maximize profit
 Provide earliest entry into market
 Minimize employee discomfort/turnover
 Decision variables
 Determine what price to use
 Determine length of time tests should be run on a new
product/service
 Determine the responsibilities to assign to each worker
 Constraints
 Can’t charge below cost
 Test enough to meet minimum safety regulations
 Ensure responsibilities are at most shared by two workers
CAPABILITIES OF A DECISION
SUPPORT SYSTEM (CONTINUED)

Decision-Making Level
DECISION MAKING PROCESS
 Managers usually make decisions by following a
four-step process (a.k.a. the scientific approach)
1. Define the problem (or opportunity)
2. Construct a model that describes the real-world
problem
3. Identify possible solutions to the modeled
problem and evaluate the solutions
4. Compare, choose, and recommend a potential
solution to the problem
DECISION MAKING IS DIFFICULT,
BECAUSE
 Technology, information systems, advanced search
engines, and globalization result in more and more
alternatives from which to choose
 Government regulations and the need for compliance,
political instability and terrorism, competition, and
changing consumer demands produce more
uncertainty, making it more difficult to predict
consequences and the future
 Other factors are the need to make rapid decisions,
the frequent and unpredictable changes that make
trial-and-error learning difficult, and the potential
costs of making mistakes
2-5: WHY ARE DECISIONS SO HARD?
The four key areas that determine the relative
difficulty of a decision are:
1. Structure – in general, the more structure,
the less information required
2. Cognitive limitations – the human mind is
limited to handling 5 to 9 distinct pieces of
information

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 27
 2-5: WHY ARE DECISIONS SO HARD? (CONT.)

The four key areas that determine the relative

difficulty of a decision are:
3. Uncertainty – the amount is based on how
complete and accurate the information is
4. Alternatives and multiple objectives – the
selection of one alternative may impede the
progress towards a different goal

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 28
 CONTINUUM OF DECISION
STRUCTURES

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 29
PHASES OF DECISION-MAKING
PROCESS
 Humans consciously or sub consciously follow
a systematic decision-making process
- Simon (1977)
1) Intelligence
2) Design
3) Choice
4) Implementation
5) (?) Monitoring (a part of intelligence?)
SIMON’S DECISION-MAKING PROCESS
 FOUR PHASES OF DECISION MAKING

McGraw-Hill © 2007 The McGraw-Hill Companies, Inc. All rights reserved.

• Simon’s Model (1977)
– Intelligence Phase
• Identification of organization goals and objectives
to an issue of concern
• Problem (or Opportunity) identification
• Problem classification – an attempt to place the
problem in a definable category, possibly leading to
a standard solution approach
• Problem decomposition – identify the sub-problems
• Problem ownership – the assignment of authority to
solve the problem
• Problem statement`
 DECISION-MAKING:
INTELLIGENCE PHASE
 Scan the environment, either intermittently
or continuously
 Identify problem situations or opportunities
 Monitor the results of the implementation
 Problem is the difference between what
people desire (or expect) and what is
actually occurring
 Symptom versus Problem
 Timely identification of opportunities is as
important as identification of problems
DISTINGUISH BETWEEN
PROBLEM & SYMPTOM
 It is important to distinguish between PROBLEMS and
SYMPTIONS.
 Iceberg Effect, useful to look for symptoms and see if
you can work back from the symptoms to the root causes
of the problems.
DECISION-MAKING:
INTELLIGENCE PHASE
 Potential issues in data/information
collection and estimation
 Lack of data
 Cost of data collection
 Inaccurate and/or imprecise data
 Data estimation is often subjective
 Data may be insecure
 Key data may be qualitative
 Data change over time (time-dependence)
DECISION-MAKING:
INTELLIGENCE PHASE
 Problem Classification
 Classification
of problems according to the degree
of structuredness
 Problem Decomposition
 Often solving the simpler subproblems may help in
solving a complex problem
 Information/data can improve the structuredness
of a problem situation
 Problem Ownership A Formal
 Outcome of intelligence phase: Problem
Statement
DECISION-MAKING: THE DESIGN
PHASE
 Finding/developing and analyzing possible
courses of actions
 A model of the decision-making problem is
constructed, tested, and validated
 Modeling: conceptualizing a problem and
abstracting it into a quantitative and/or
qualitative form (i.e., using symbols/variables)
 Abstraction: making assumptions for simplification
 Tradeoff (cost/benefit): more or less abstraction
 Modeling: both an art and a science
DECISION-MAKING: THE DESIGN
PHASE
 Selection of a Principle of Choice
 It is a criterion that describes the acceptability
of a solution approach
 Reflection of decision-making objective(s)
 In a model, it is the result variable
 Choosing and validating against
 High-risk versus low-risk
 Optimize versus satisfice
 Criterion is not a constraint
 DECISION-MAKING: THE DESIGN
PHASE
 Normative models (= optimization)
 the chosen alternative is demonstrably the best of all
possible alternatives
 Assumptions of rational decision makers
 Humans are economic beings whose objective is to maximize
the attainment of goals
 For a decision-making situation, all alternative courses of
action and consequences are known
 Decision makers have an order or preference that enables
them to rank the desirability of all consequences
DECISION-MAKING: THE DESIGN
PHASE
 Heuristic models (= suboptimization)
 the chosen alternative is the best of only a subset of
possible alternatives
 Often, it is not feasible to optimize realistic
(size/complexity) problems
 Suboptimization may also help relax unrealistic
assumptions in models
 Help reach a good enough solution faster
DECISION-MAKING: THE DESIGN
PHASE
 Descriptive models
 describe things as they are or as they are believed to
be (mathematically based)
 They do not provide a solution but information that
may lead to a solution
 Simulation - most common descriptive modeling
method (mathematical depiction of systems in a
computer environment)
 Allows experimentation with the descriptive model of
a system
DECISION-MAKING: THE DESIGN
PHASE
 Good Enough, or Satisficing
“something less than the best”
 A form of suboptimization
 Seeking to achieving a desired level of performance as
opposed to the “best”
 Benefit: time saving

 Simon’s idea of bounded rationality

DECISION-MAKING: THE DESIGN
PHASE
 Developing (Generating) Alternatives
 In optimization models (such as linear programming),
the alternatives may be generated automatically
 In most MSS situations, however, it is necessary to
generate alternatives manually
 Use of GSS helps generating alternatives
 Measuring/ranking the outcomes
 Using the principle of choice
DECISION-MAKING: THE DESIGN
PHASE
 Risk
 Lack of precise knowledge (uncertainty)
 Risk can be measured with probability
 Scenario (what-if case)
A statement of assumptions about the operating
environment (variables) of a particular system at a
given time
 Possible scenarios: best, worst, most likely, average
(and custom intervals)
– Choice Phase
• Selects the possible alternative by identified
criteria
• Elapsed time from problem identification to Choice
phase may be significant
• With internal feedback loops
• FOUR searching approaches
– Analytical Technique (i.e., solving a formula)
– Algorithms (i.e. step-by-step procedures)
– Heuristics (i.e. rules of thumb)
– Blind searches (i.e. shooting in the dark)
• THREE analysis approaches
– Sensitivity analysis (Only one variable is changed
but several times)
– What-if analysis (Change different variables and
observe how the changes to these variables affect
other variables)
– Goal Seeking (Target is set and selected variables are
changed until target is achieved)
 DECISION-MAKING: THE CHOICE
PHASE
 The actual decision and the commitment to
follow a certain course of action are made
here
 The boundary between the design and choice
is often unclear (partially overlapping phases)
 Generate alternatives while performing evaluations
 Includes the search, evaluation, and
recommendation of an appropriate solution to
the model
 Solving the model versus solving the problem!
2-10: THE PROCESS OF CHOICE
 In Simon’s model, the choice phase
represents the climax of the decision
process.
 It is important, however, to NOT focus all
the energy here because it will not do justice
to the other phases.
 The choice phase focuses mainly on decisions
of the semistructured and unstructured types
where there is uncertainty.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 48
DECISION-MAKING: THE CHOICE
PHASE
 Search approaches
 Analytic techniques (solving with a formula)
 Algorithms (step-by-step procedures)
 Heuristics (rule of thumb)
 Blind search (truly random search)
 Additional activities
 Sensitivityanalysis
 What-if analysis
 Goal seeking
NORMATIVE VERSUS DESCRIPTIVE CHOICE
 In normative models of decision making,
choice is the theory in itself. In a behavioral
or descriptive model, choice is one step in a
process.
 A DSS will handle uncertainty by assigning
probabilities to the expected decision
outcome -- an activity more a part of a
normative rather than behavioral process.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 50
PERCEPTION
This is a special type of cognitive limitation.
Common perception blocks are:
 Difficulty in isolating the problem.
 Delimiting the problem space too closely.
 Inability to see the problem from different
perspectives.
 Stereotyping.
 Cognitive saturation or overload.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 51
JUDGMENT
 Although numerous strategies exist for
evaluation of solution alternatives, judgment
appears to be the most favored.
 Compared to detailed analysis, judgment is
faster, more convenient, and less stressful.
 When applied in isolation, however,
judgment may be nothing but a guess.
 One reason why it may not be used
exclusively is that it relies heavily on the
decision maker’s recollection, which may
fail.
Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter
Prentice-Hall 2 - 52
2-12:
BIASES AND HEURISTICS IN DECISION MAKING

 We all have “rules of thumb” that we rely on

in making decisions. Another term for such
rules is heuristics.
 Heuristic search techniques follow a series of
steps based on “rules” developed by
experience.
 These searches can often provide solutions
very close to those found by exhaustive
search.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 53
ADVANTAGES OF HEURISTICS IN PROBLEM SOLVING

 Simple to understand
 Easy to implement.
 Requires less conception time.
 Requires less cognitive effort.
 Can produce multiple solutions.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 54
APPROPRIATE USES OF HEURISTICS IN
PROBLEM SOLVING
 Input data are inexact or limited.
 High computation time for an optimal solution.
 Problems are solved frequently and repeatedly.
 Symbolic processing is involved.
 A reliable, exact method is not available.
 Optimization is not economically feasible.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 55
TRAVELING
SALESMAN
PROBLEM

CITIES TO
VISIT

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 56
 INITIAL HEURISTIC SOLUTION
RULE: START AT HOME, GO TO CLOSEST CITY

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 57
 MODIFIED HEURISTIC SOLUTION
RULE: NO CROSSING ANY CONNECTION, NO BACKTRACKING

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 58
HEURISTIC BIAS
Sometimes the use of heuristics can hamper
finding a solution. The four major
categories of bias are:
1. Availability – people tend to estimate
probability based on past experience,
which may not be representative.
2. Adjustment and anchoring – people often
pick a starting value and then adjust up
and down from it. They tend to
underestimate the need for adjustments.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 59
HEURISTIC BIAS (CONT.)
Sometimes the use of heuristics can hamper
finding a solution. The four major
categories of bias are:
3. Representativeness – people tend to
misestimate probabilities of belonging to a
group.
4. Motivational – incentives often lead
decision makers to estimate probabilities
that do not reflect their true beliefs.

Marakas: Decision Support Systems, 2nd Edition © 2003, Chapter

Prentice-Hall 2 - 60
 – Implementation Phase
• Putting a recommended solution to work, not
necessarily implementing a computer system.

Source: Figure 2.1, P46, Decision making, systems, modeling and support, Turban, E 2011,
Decision Support and business intelligence systems, 9th ed, Prentice Hall, Boston
DECISION-MAKING:
THE IMPLEMENTATION PHASE
“Nothing more difficult to carry out, nor more
doubtful of success, nor more dangerous to
handle, than to initiate a new order of things.”
- The Prince, Machiavelli 1500s
 Solution to a problem = Change
 Change management?
 Implementation: putting a recommended solution
to work
HOW DECISIONS ARE
SUPPORTED
HOW DECISIONS ARE
SUPPORTED
 Support for the Intelligence Phase
 Enabling continuous scanning of external and internal
information sources to identify problems and/or
opportunities
 Resources/technologies: Web; ES, OLAP, data
warehousing, data/text/Web mining,
EIS/Dashboards, KMS, GSS, GIS,…
 Business activity monitoring (BAM)
 Business process management (BPM)
 Product life-cycle management (PLM)
HOW DECISIONS ARE
SUPPORTED
 Support for the Design Phase
 Enablinggenerating alternative courses of action,
determining the criteria for choice
 Generating alternatives
 Structured/simple problems: standard and/or special
models
 Unstructured/complex problems: human experts, ES, KMS,
brainstorming/GSS, OLAP, data/text mining
 A good “criteria for choice” is critical!
HOW DECISIONS ARE
SUPPORTED
 Support for the Choice Phase
 Enabling selection of the best alternative given a
complex constraint structure
 Use sensitivity analyses, what-if analyses, goal
seeking
 Resources
 KMS
 CRM, ERP, and SCM
 Simulation and other descriptive models
 HOW DECISIONS ARE
SUPPORTED

 Support for the Implementation Phase

 Enabling implementation/deployment of the selected
solution to the system
 Decision communication, explanation and
justification to reduce resistance to change
 Resources
 Corporate portals, Web 2.0/Wikis
 Brainstorming/GSS
 KMS , ES