© 2005 prentice hall, decision support systems and intelligent systems, 7th edition, turban,...

© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang

2-1

Chapter 2Decision-Making Systems,

Models, and Support

Turban, Aronson, and Liang Decision Support Systems and Intelligent

Systems, Seventh Edition


2-2

Learning Objectives

• Learn the basic concepts of decision making.• Understand systems approach.• Learn Simon’s four phases of decision making.• Understand the concepts of rationality and

bounded rationality.• Differentiate betwixt making a choice and

establishing a principle of choice.• Learn which factors affect decision making.• Learn how DSS supports decision making in

practice.


2-3

Standard Motor Products Shifts Gears Into Team-Based Decision-

Making Vignette

• Team-based decision making– Increased information sharing– Daily feedback– Self-empowerment– Idea generation– Time/Quality aspect of the decision

• Shifting responsibility towards teams

• Elimination of middle management


2-4

Standard Motor Products Shifts Gears Into Team-Based Decision-

Making Vignette

• Shifting responsibility towards teams-based decisions.

1.Produce Quality Decisions.

2.Sharing Responsibility, experiences.

3.Self-Empowerment.

4.Improve implementation.

5.Because of higher risks, org. volume.


2-5

Decision Making 1-3Problem Solving 1-4

• Process of choosing amongst alternative courses of action for the purpose of attaining a goal or goals.

• The four phases of the decision process are:1. Intelligence 2. Design3. Choice4. implementation


2-6

Systems

• Structure– Inputs– Processes– Outputs– Feedback from output to decision maker

• Separated from environment by boundary• Surrounded by environment

Input Processes Outputboundary

Environment


2-7


2-8

System Types

• Closed system– Independent– Takes no inputs– Delivers no outputs to the environment– Black Box

• Open system– Accepts inputs– Delivers outputs to environment


2-9

Models Used for DSS

• Iconic– Small physical replication of system

• Analog– Behavioral representation of system– May not look like system

• Quantitative (mathematical)– Demonstrates relationships between

systems


2-10


2-11

Phases of Decision-Making

• Simon’s original three phases:– Intelligence– Design– Choice

• He added fourth phase later:– Implementation (putting words into action)

• Book adds fifth stage:– Monitoring (Evaluation, Control)


2-12

Decision-Making Intelligence Phase

Scan the environment (Identify Problem, Situation, Opportunity)

• Analyze organizational goals• Collect data• Identify problem• Categorize problem

– Programmed and non-programmed– Decomposed into smaller parts

• Assess ownership and responsibility for problem resolution


2-13

Decision-Making Design Phase

• Develop alternative courses of action• Analyze potential solutions• Create model• Test for feasibility • Validate results• Select a principle of choice

– Establish objectives– Incorporate into models– Risk assessment and acceptance– Criteria and constraints


2-14

Decision-Making Choice Phase

• Principle of choice– Describes acceptability of a solution approach. (Willingness to

assume high or low risk, optimization .

• Normative Models– Optimization

• Effect of each alternative– Rationalization (only for human ????!!!!!!)

• More of good things, less of bad things• Courses of action are known quantity• Options ranked from best to worse

– Suboptimization• Decisions made in separate parts of organization without

consideration of whole


2-15

Descriptive Models

• Describe how things are believed to be

• Typically, mathematically based• Applies single set of alternatives• Examples:

– Simulations– What-if scenarios– Scenario analysis– Financial planning.


2-16

Developing Alternatives

• Generation of alternatives– May be automatic or manual– May be legion, leading to information

overload– Scenarios– Evaluate with heuristics– Outcome measured by goal attainment

And Achievements.

Alternative Evaluation

To evaluate and compare each proposed alternatives it is necessary to predict the future outcome of each alternative.

Decision Situation:


2-17

RISKUncertaintyIgnorance

Certainty Complete

Knowledge

Decision Situation

• Decision Making under certainty.Complete knowledge is available

• Decision making under risk.Probabilistic or stochastic, Calculated risk (Risk Analysis)

• Decision making under Uncertainty

No knowledge, estimate or probability


2-18

Measuring Outcomes and goals

• Outcome: Profit.

• Goal: Max. Profit.

• Outcome: Customer Satisfaction can be measured by complaints


2-19

ScenariosPossible scenarios:• The worst possible.

• The best possible.

• The most likely.

• The Average.


2-20

Errors in D.M.

• DM is based on a model.

• DM errors are possible due to structural errors in the model.

• It is critical to evaluate the model.

• Gather the correct amount of info. With the right level of precision and accuracy.


2-21

DM 7 Deadly sins. Sawyer ‘99

Common pitfalls decision makers often unwittingly encounter.

1. Believing that you know all the answer (no attempt to seek outside information or expertise).

2. Asking the wrong Questions. You need the right info.

3. Ego, refuse to back down from bad policy or decision.

4. Saving money by not seeking out info. IS or Expert.

5. Copying. If it works for them it’ll works for us.

6. Ignore negative advice. Kill the messenger with the bad news.

7. Making no decision can be the same as making a bad decision. Procrastination is not necessary a good management techniques.


2-22


2-23

Problems

• Satisficing is the willingness to settle for less than ideal or perfect or the best (Satisfactory).– Form of suboptimization

• Bounded rationality – Limited human capacity– Limited by individual differences and

biases

• Too many choices


2-24

2.8 DM Choice Phase

• Decision making with commitment to act. Choice is the critical act of DM

• Search Approaches Determine the appropriate courses of action– Analytical techniques (mathematically derive optimal solution)

– Algorithms (Step by step search process)

– Heuristics (With rules to guide the search)

– Blind search (Arbitrary, not guided search)

• Analyze for robustness

Analytical Techniques

• Mathematically deriving the optimal solution.

• Used mainly in structured problems.

• At tactical or operational level.


2-25

Algorithms

• Algorithm: is a step-by-step search process for optimal solution.

• May be used by Analytical Techniques to increase efficiency.

• Algorithm process continue to improve reached solution until objective value is found.


2-26

Blind search

A two arbitrary search approach that is not guided.

1- complete search of all possible alternative until optimal solution is found.

2- Partial search which continue until good enough solution is found.


2-27

Heuristic search Heurism Discovery

Are decision rules governing how a problem should be solved.


2-28

Example of Heuristics

Sequence jobs through a machine.

Do the jobs that require the least time first.

Purchase stocks If a price-to-earning ratio exceeds 10, do not buy.

Travel Do not use the freeway between 9 and 10

Capital investment Consider projects with less than 2yearspay back period

Purchase of a house In good neighborhood, but only in lower price range.

2.9 Evaluation

The search process discribed earlier is coupled with evaluation. Evaluation is the final step that leads to a recommended solution.


2-29

Multiple Goals

Management decision aims at evaluating how far each alternative advances mgmt towards its GOALS.

Today’s mgmt systems are much more complex and managers want to attain CONFLICTING MULTIPLE GOALS.

GOALS:

1- Profit-making.

2- Growth

3- Development ( Market and product and employees)

4- Provide job security.

5- Serve the local community.

6- Satisfying the stackeholders

7- Enjoy high salaries


2-30

Sensitivity Analysis

Attempts to assess the impact of in the input data or parameters on the proposed solution.

• The impact of changes in external (uncontrollable) variables and parameters on outcome variable(s).

• The impact of changes in decision variables on outcome variable(s).

• The effect of uncertainty in estimating external variables.

• The robustness of decisions under changing conditions.


2-31

What-If Analysis

What will happen to the solution if an input variable, an assumption, or parameter value is changed???

• What will happen to the total inventory cost if the cost of carrying inventory increases by 10%.

• What will be the market share if the advertising budget increases by 5%.

See figures 2.9 pp.66


2-32

Goal Seeking

Backward solution approach, to calculate the value of input necessary to achieve a desired level of an output GOAL.

• What annual R&D budget is needed for an annual growth rate of 15%.

• How many nurses are needed to reduce the average waiting time of patients in the emergency room to less than 10 minutes.

See figures 2.10 PP. 66


2-33


2-34

2.10 Decision-Making Implementation Phase

• Putting recomm. solution to work.

• A process with vague, ambiguous, uncertain and unclear boundaries which include:– Dealing with resistance to change– User training (Empowerment)– Upper management support.

Individual Experience Realizing CHANGE

• Clear vision and objectives.

• Strategic plan.

• Top management support.

• Awareness through empowerment.

• Participation.

• Involvement.

• Strong, good will and Persistence, Diligence


2-35


2-36

Source: Based on Sprague, R.H., Jr., “A Framework for the Development of DSS.” MIS Quarterly, Dec. 1980, Fig. 5, p. 13.


2-37

Decision Support Systems

• Intelligence Phase– Automatic

• Data Mining– Expert systems, CRM, neural networks

– Manual• OLAP• KMS

– Reporting• Routine and ad hoc


2-38


• Design Phase– Financial and forecasting models– Generation of alternatives by expert

system– Relationship identification through OLAP

and data mining– Recognition through KMS– Business process models from CRM,

RMS, ERP, and SCM


2-39


• Choice Phase– Identification of best alternative– Identification of good enough alternative– What-if analysis– Goal-seeking analysis– May use KMS, GSS, CRM, ERP, and

SCM systems


2-40


• Implementation Phase– Improved communications– Collaboration– Training– Supported by KMS, expert systems,

GSS


2-41

Decision-Making In Humans

• Temperament– Hippocrates’ personality types– Myers-Briggs’ Type Indicator– Kiersey and Bates’ Types and

Motivations– Birkman’s True Colours

• Gender


2-42

Decision-Making In Humans

• Cognitive styles– What is perceived?– How is it organized?– Subjective

• Decision styles– How do people think?– How do they react?– Heuristic, analytical, autocratic

highhanded, democratic, consultative


2-43

© 2005 prentice hall, decision support systems and intelligent systems, 7th edition, turban,...

Documents