Turbanchap02discription material require.ppt

1
CHAPTER 2
Decision Making, Systems,
Modeling, and Support

2
Decision Making, Systems,
Modeling, and Support
 Conceptual Foundations of Decision Making
 The Systems Approach
 How Support is Provided
 Opening Vignette:
How to Invest $10,000,000
Decision Support Systems and Intelligent Systems, Efraim Turban and Jay E. Aronson, 6th edition,
Copyright 2001, Prentice Hall, Upper Saddle River, NJ

3
Typical Business Decision Aspects
 Decision may be made by a group
 Group member biases
 Groupthink
 Several, possibly contradictory objectives
 Many alternatives
 Results can occur in the future
 Attitudes towards risk
 Need information
 Gathering information takes time and expense
 Too much information
 “What-if” scenarios
 Trial-and-error experimentation with the real system may result in a loss
 Experimentation with the real system - only once
 Changes in the environment can occur continuously
 Time pressure

4
 How are decisions made???
 What methodologies can be applied?
 What is the role of information systems in supporting decision
making?
DSS
 Decision
 Support
 Systems

5
Decision Making
 Decision Making: a process of choosing among
alternative courses of action for the purpose of
attaining a goal or goals
 Managerial Decision Making is synonymous with
the whole process of management (Simon, 1977)

6
Decision Making versus
Problem Solving
Simon’s 4 Phases of Decision Making
1. Intelligence
2. Design
3. Choice
4. Implementation
Decision making and problem solving
are interchangeable

7
Systems
 A SYSTEM is a collection of objects such as
people, resources, concepts, and procedures
intended to perform an identifiable function or to
serve a goal
 System Levels (Hierarchy): All systems are
subsystems interconnected through interfaces

8
The Structure of a System
Three Distinct Parts of Systems (Figure 2.1)
 Inputs
 Processes
 Outputs
Systems
 Surrounded by an environment
 Frequently include feedback
The decision maker is usually considered part of the system

9
System
Input(s)
Feedback
Environment
Output(s)
Boundary
Processes

10
 Inputs are elements that enter the system
 Processes convert or transform inputs into outputs
 Outputs describe finished products or consequences of being in the system
 Feedback is the flow of information from the output to the decision
maker, who may modify the inputs or the processes (closed loop)
 The Environment contains the elements that lie outside but impact the
system's performance

11
How to Identify the Environment?
Two Questions (Churchman, 1975)
1. Does the element matter relative to the system's goals?
[YES]
2. Is it possible for the decision maker to significantly
manipulate this element? [NO]

12
Environmental Elements Can Be
 Social
 Political
 Legal
 Physical
 Economical
 Often Other Systems

13
The Boundary Separates a
System From Its Environment
Boundaries may be physical or nonphysical (by definition
of scope or time frame)
Information system boundaries are usually by definition!

14
Closed and Open Systems
Defining manageable boundaries is closing the system
 A Closed System is totally independent of other systems
and subsystems
 An Open System is very dependent on its environment

15
An Information System
 Collects, processes, stores, analyzes, and
disseminates information for a specific purpose
 Is often at the heart of many organizations
 Accepts inputs and processes data to provide
information to decision makers and helps decision
makers communicate their results

16
System Effectiveness and Efficiency
Two Major Classes of Performance Measurement
 Effectiveness is the degree to which goals are achieved
Doing the right thing!
 Efficiency is a measure of the use of inputs (or resources) to
achieve outputs
Doing the thing right!
 MSS emphasize effectiveness
Often: several non-quantifiable, conflicting goals

17
Models
 Major component of DSS
 Use models instead of experimenting on the real system
 A model is a simplified representation or abstraction of
reality.
 Reality is generally too complex to copy exactly
 Much of the complexity is actually irrelevant in
problem solving

18
Degrees of Model Abstraction
(Least to Most)
 Iconic (Scale) Model: Physical replica of a system
 Analog Model behaves like the real system but does not
look like it (symbolic representation)
 Mathematical (Quantitative) Models use mathematical
relationships to represent complexity
Used in most DSS analyses

19
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.
Computer graphics advances: more iconic and analog
models (visual simulation)

20
The Modeling Process--
A Preview
 How Much to Order for the Ma-Pa Grocery?
 Bob and Jan: How much bread to stock each day?
Solution Approaches
 Trial-and-Error
 Simulation
 Optimization
 Heuristics

21
The Decision-Making Process
Systematic Decision-Making Process (Simon, 1977)
 Intelligence
 Design
 Choice
 Implementation
(Figure 2.2)
Modeling is Essential to the Process

22
 Intelligence phase
– Reality is examined
– The problem is identified and defined
 Design phase
– Representative model is constructed
– The model is validated and evaluation criteria are set
 Choice phase
– Includes a proposed solution to the model
– If reasonable, move on to the
 Implementation phase
– Solution to the original problem
Failure: Return to the modeling process
Often Backtrack / Cycle Throughout the Process

23
The Intelligence Phase
Scan the environment to identify problem situations or
opportunities
Find the Problem
 Identify organizational goals and objectives
 Determine whether they are being met
 Explicitly define the problem

24
Problem Classification
Structured versus Unstructured
Programmed versus Nonprogrammed Problems
Simon (1977)
Nonprogrammed Programmed
Problems Problems

25
 Problem Decomposition: Divide a complex problem into (easier to solve)
subproblems
Chunking (Salami)
 Some seemingly poorly structured problems may have some highly structured
subproblems
 Problem Ownership
Outcome: Problem Statement

26
The Design Phase
 Generating, developing, and analyzing
possible courses of action
Includes
 Understanding the problem
 Testing solutions for feasibility
 A model is constructed, tested, and validated
Modeling
 Conceptualization of the problem
 Abstraction to quantitative and/or qualitative forms

27
Mathematical Model
 Identify variables
 Establish equations describing their relationships
 Simplifications through assumptions
 Balance model simplification and the accurate
representation of reality
Modeling: an art and science

28
Quantitative Modeling Topics
 Model Components
 Model Structure
 Selection of a Principle of Choice
(Criteria for Evaluation)
 Developing (Generating) Alternatives
 Predicting Outcomes
 Measuring Outcomes
 Scenarios

29
Components of
Quantitative Models
 Decision Variables
 Uncontrollable Variables (and/or Parameters)
 Result (Outcome) Variables
 Mathematical Relationships
or
 Symbolic or Qualitative Relationships
(Figure 2.3)

30
 Decision
 Uncontrollable Factors
 Relationships among Variables
Results of Decisions are
Determined by the

31
Result Variables
 Reflect the level of effectiveness of the system
 Dependent variables
 Examples - Table 2.2

32
Decision Variables
 Describe alternative courses of action
 The decision maker controls them

33
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
Intermediate Result Variables
 Reflect intermediate outcomes

34
The Structure of Quantitative
Models
 Mathematical expressions (e.g., equations or
inequalities) connect the components
 Simple financial model
P = R - C
 Present-value model
P = F / (1+i)n

35
LP Example
The Product-Mix Linear Programming Model
 MBI Corporation
 Decision: How many computers to build next month?
 Two types of computers
 Labor limit
 Materials limit
 Marketing lower limits
Constraint CC7 CC8 Rel Limit
Labor (days) 300 500 <= 200,000 / mo
Materials $ 10,000 15,000 <= 8,000,000/mo
Units 1 >= 100
Units 1 >= 200
Profit $ 8,000 12,000 Max
Objective: Maximize Total Profit / Month

36
Linear Programming Model
 Components
Decision variables
Result variable
Uncontrollable variables (constraints)
 Solution
X1 = 333.33
X2 = 200
Profit = $5,066,667

37
Optimization Problems
 Linear programming
 Goal programming
 Network programming
 Integer programming
 Transportation problem
 Assignment problem
 Nonlinear programming
 Dynamic programming
 Stochastic programming
 Investment models
 Simple inventory models
 Replacement models (capital budgeting)

38
The Principle of Choice
 What criteria to use?
 Best solution?
 Good enough solution?

39
Selection of a
Principle of Choice
Not the choice phase
A decision regarding the acceptability
of a solution approach
 Normative
 Descriptive

40
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

41
Rationality Assumptions
 Humans are economic beings whose objective is to maximize
the attainment of goals; that is, the decision maker is
rational
 In a given decision situation, all viable alternative courses of
action and their consequences, or at least the probability and
the values of the consequences, are known
 Decision makers have an order or preference that enables
them to rank the desirability of all consequences of the
analysis

42
Suboptimization
 Narrow the boundaries of a system
 Consider a part of a complete system
 Leads to (possibly very good, but) non-optimal
solutions
 Viable method

43
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
 Simulation: Descriptive modeling technique

44
Descriptive Models
 Information flow
 Scenario analysis
 Financial planning
 Complex inventory decisions
 Markov analysis (predictions)
 Environmental impact analysis
 Simulation
 Waiting line (queue) management

45
Satisficing (Good Enough)
 Most human decision makers will settle for a good
enough solution
 Tradeoff: time and cost of searching for an
optimum versus the value of obtaining one
 Good enough or satisficing solution may meet a
certain goal level is attained
(Simon, 1977)

46
Why Satisfice?
Bounded Rationality (Simon)
 Humans have a limited capacity for rational thinking
 Generally construct and analyze a simplified model
 Behavior to the simplified model may be rational
 But, the rational solution to the simplified model may
NOT BE rational in the real-world situation
 Rationality is bounded by
– limitations on human processing capacities
– individual differences
 Bounded rationality: why many models are descriptive,
not normative

47
Developing (Generating) Alternatives
 In Optimization Models: Automatically by the Model!
Not Always So!
 Issue: When to Stop?

48
Predicting the Outcome of Each
Alternative
 Must predict the future outcome of each proposed
alternative
 Consider what the decision maker knows (or
believes) about the forecasted results
 Classify Each Situation as Under
– Certainty
– Risk
– Uncertainty

49
Decision Making Under Certainty
 Assumes complete knowledge available
(deterministic environment)
 Example: U.S. Treasury bill investment
 Typically for structured problems with short
time horizons
 Sometimes DSS approach is needed for certainty
situations

50
Decision Making Under Risk
(Risk Analysis)
 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
 Assess the (calculated) degree of risk associated with
each alternative

51
Risk Analysis
 Calculate the expected value of each alternative
 Select the alternative with the best expected value
 Example: poker game with some cards face up (7
card game - 2 down, 4 up, 1 down)

52
Decision Making Under Uncertainty
 Several outcomes possible for each course of action
 BUT the decision maker does not know, or cannot
estimate the probability of occurrence
 More difficult - insufficient information
 Assessing the decision maker's (and/or the
organizational) attitude toward risk
 Example: poker game with no cards face up (5 card
stud or draw)

53
Measuring Outcomes
 Goal attainment
 Maximize profit
 Minimize cost
 Customer satisfaction level (minimize number of
complaints)
 Maximize quality or satisfaction ratings (surveys)

54
Scenarios
Useful in
 Simulation
 What-if analysis

55
Importance of Scenarios in MSS
 Help identify potential opportunities and/or
problem areas
 Provide flexibility in planning
 Identify leading edges of changes that management
should monitor
 Help validate major assumptions used in modeling
 Help check the sensitivity of proposed solutions to
changes in scenarios

56
Possible Scenarios
 Worst possible (low demand, high cost)
 Best possible (high demand, high revenue, low cost)
 Most likely (median or average values)
 Many more
 The scenario sets the stage for the analysis

57
The Choice Phase
 The CRITICAL act - decision made here!
 Search, evaluation, and recommending an appropriate
solution to the model
 Specific set of values for the decision variables in a selected
alternative
The problem is considered solved only after the
recommended solution to the model is successfully
implemented

58
Search Approaches
 Analytical Techniques
 Algorithms (Optimization)
 Blind and Heuristic Search Techniques

59
Evaluation: Multiple Goals,
Sensitivity Analysis, What-If, and
Goal Seeking
 Evaluation (with the search process) leads to a
recommended solution
 Multiple goals
 Complex systems have multiple goals
Some may conflict
 Typically, quantitative models have a single goal
 Can transform a multiple-goal problem into a single-
goal problem

60
Common Methods
 Utility theory
 Goal programming
 Expression of goals as constraints, using linear
programming
 Point system
 Computerized models can support multiple
goal decision making

61
Sensitivity Analysis
 Change inputs or parameters, look at model results
Sensitivity analysis checks relationships
Types of Sensitivity Analyses
 Automatic
 Trial and error

62
Trial and Error
 Change input data and re-solve the
problem
 Better and better solutions can be
discovered
 How to do? Easy in spreadsheets
(Excel)
– What-if
– Goal seeking

63
What-If Analysis
 Figure 2.9 - Spreadsheet example of a what-if query for a cash
flow problem

64
Goal Seeking
 Backward solution approach
 Example: Figure 2.10
What interest rate causes an the net present value of an
investment to break even?
 In a DSS the what-if and the goal-seeking options must
be easy to perform

65
Goal Seeking

66
The Implementation Phase
There is nothing more difficult to carry out, nor more doubtful of
success, nor more dangerous to handle, than to initiate a new order
of things
(Machiavelli, 1500s)
*** The Introduction of a Change ***
Important Issues
 Resistance to change
 Degree of top management support
 Users’ roles and involvement in system development
 Users’ training

67
How Decisions Are Supported
Specific MSS technologies relationship to the decision
making process (see Figure 2.10)
 Intelligence: DSS, ES, ANN, MIS, Data Mining,
OLAP, EIS, GSS
 Design and Choice: DSS, ES, GSS, Management
Science, ANN
 Implementation: DSS, ES, GSS

68
Alternative Decision Making Models
 Paterson decision-making process
 Kotter’s process model
 Pound’s flow chart of managerial behavior
 Kepner-Tregoe rational decision-making approach
 Hammond, Kenney, and Raiffa smart choice method
 Cougar’s creative problem solving concept and model
 Pokras problem-solving methodology
 Bazerman’s anatomy of a decision
 Harrison’s interdisciplinary approaches
 Beach’s naturalistic decision theories

69
Naturalistic Decision Theories
 Focus on how decisions are made, not how they should
be made
 Based on behavioral decision theory
 Recognition models
 Narrative-based models

70
Recognition Models
 Policy
 Recognition-primed decision model

71
Narrative-based Models (Descriptive)
 Scenario model
 Story model
 Argument-driven action (ADA) model
 Incremental models
 Image theory

72
Other Important Decision-
Making Issues
 Personality types
 Gender
 Human cognition
 Decision styles

73
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

74
Temperament
 Jung (1923): people are fundamentally different
 Hippocrates, too
 Myers-Briggs personality profile (DSS in Focus
2.10)
 Keirsey and Bates: short Myers-Briggs test
 Birkman True Colors: Short test (DSS in Focus
2.11)

75
Myers-Briggs Dimensions
 Extraversion (E) to Intraversion (I)
 Sensation (S) to Intuition (N)
 Thinking (T) to Feeling (F)
 Perceiving (P) to Judging (J)

76
Birkman True Colors Types
Red
Blue
Green
Yellow

77
Gender
 Sometimes empirical testing indicates
gender differences in decision making
 Results are overwhelmingly inconclusive

78
Cognition
 Cognition: Activities by which an individual resolves
differences between an internalized view of the
environment and what actually exists in that same
environment
 Ability to perceive and understand information
 Cognitive models are attempts to explain or understand
various human cognitive processes

79
Cognitive Style
 The subjective process through which individuals perceive,
organize, and change information during the decision-making
process
 Often determines people's preference for human-machine
interface
 Impacts on preferences for qualitative versus quantitative
analysis and preferences for decision-making aids
 Affects the way a decision maker frames a problem

80
Cognitive Style Research
 Impacts on the design of management information systems
 May be overemphasized
 Analytic decision maker
 Heuristic decision maker

81
Decision Styles
The manner in which decision makers
 Think and react to problems
 Perceive their
– Cognitive response
– Values and beliefs
 Varies from individual to individual and from situation to situation
 Decision making is a nonlinear process
The manner in which managers make decisions (and the way they interact
with other people) describes their decision style
 There are dozens

82
Some Decision Styles
 Heuristic
 Analytic
 Autocratic
 Democratic
 Consultative (with individuals or groups)
 Combinations and variations
 For successful decision-making support, an MSS must
fit the
– Decision situation
– Decision style

83
 The system
– should be flexible and adaptable to different users
– have what-if and goal seeking
– have graphics
– have process flexibility
 An MSS should help decision makers use and develop their own
styles, skills, and knowledge
 Different decision styles require different types of support
 Major factor: individual or group decision maker

84
The Decision Makers
 Individuals
 Groups

85
Individuals
 May still have conflicting objectives
 Decisions may be fully automated

86
Groups
 Most major decisions made by groups
 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)
 Organizational DSS can help in enterprise-wide decision-making
situations

87
Summary
 Managerial decision making is the whole process of
management
 Problem solving also refers to opportunity's evaluation
 A system is a collection of objects such as people, resources,
concepts, and procedures intended to perform an identifiable
function or to serve a goal
 DSS deals primarily with open systems
 A model is a simplified representation or abstraction of reality
 Models enable fast and inexpensive experimentation with
systems

88
 Modeling can employ optimization, heuristic, or simulation techniques
 Decision making involves four major phases: intelligence, design,
choice, and implementation
 What-if and goal seeking are the two most common sensitivity analysis
approaches
 Computers can support all phases of decision making by automating
many required tasks
 Personality (temperament) influences decision making
 Gender impacts on decision making are inconclusive
 Human cognitive styles may influence human-machine interaction
 Human decision styles need to be recognized in designing MSS

Turbanchap02discription material require.ppt

More Related Content

Similar to Turbanchap02discription material require.ppt (20)

More from YumnaShahzaad (18)

Recently uploaded (20)

Turbanchap02discription material require.ppt