IS5740: Management Support Systems Narsi Bolloju

1
IS5740 Management Support Systems Narsi
Bolloju

• Lecture 2
• Decision Models, Modeling
• and Support (source Turban 1998, Chapter 2)

2
Overview

• Typical Aspects of Business Decision
• Models
• The Decision Making Process
• How Decisions are Supported

3
Typical Aspects of Decision Problems

• Decision may be made by a group
• Several, possibly contradictory objectives
• Hundreds or thousands of alternatives
• Results can occur in the future
• Attitudes towards risk
• "What-if" scenarios
• Trial-and-error experimentation with the real
  system may result in a loss
• Experimentation with the real system can only be
  done once
• Changes in the environment can occur continuously
  

4
Decision Models

• A 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)

5
Decision Models (contd.)

• Models can be classified, according to their
  degree of abstraction, into
• Iconic (scale) models.
• Analog models.
• Mathematical (Quantitative) models.
• Qualitative models.

6
Benefits of Models

• Time compression
• Easy model manipulation
• Low cost of construction
• Low cost of execution (especially that of errors)
  
• Can model risk and uncertainty
• Can model large and extremely complex systems
  with possibly infinite solutions
• Enhance and reinforce learning, and enhance
  training

7
The Modeling Process

• trial and error (too many trails very high cost
  of making errors difficult due to the changes in
  the environment)
• simulation (no guarantee that the best one is
  found cost and effort in building simulation
  models)
• optimization (requires that the problems are
  structured)
• heuristics (based on the experience no guarantee
  that the best one is found)

8
The Decision Making Process (Simon)
Reality
simplification
Intelligence Phase
assumptions
Problem statement
Design Phase
Validation of the model
Alternatives
Verification, Testing of Proposed solution
Choice Phase
success
solution
result
Implementation Phase
failure
9
The Intelligence Phase

• finding the problem
• problem classification
• problem decomposition
• problem ownership

10
The Design Phase

• components of quantitative models (the components
  of a quantitative model are tied together by sets
  of mathematical expressions such as equations or
  inequalities)
• structure of quantitative models
• selection of a principle of choice
• normative models
• suboptimization
• descriptive models
• good enough or satisficing

11
The Design Phase (contd.)

• developing (generating) alternatives
• predicting the outcome of each alternative
• decision making under certainty
• decision making under risk
• decision making under uncertainty
• measuring outcomes (goals' attainment level)
• scenarios

12
The Choice Phase

• search approaches
• optimization (analytical)
• blind search (complete enumeration/ exhaustive or
  partial search)
• heuristic search

13
Evaluation of Alternatives

• multiple goals vs. single measure of
  effectiveness
• sensitivity analysis for flexibility
  adaptability and better understanding of the
  model
• types of sensitivity analysis automatic and
  trial error
• "what-if" analysis for verify the impact of a
  change in the input data on the proposed solution
  
• goal seeking analysis to find the inputs
  necessary to achieve a desired level of an output
  (goal)

14
The Implementation Phase

• the implementation of a proposed solution to a
  problem is the introduction of change
• importance in dealing with generic issues such as
  resistance to change, degree of top management
  support, user's training, ...

15
How Decisions are Supported
ANN, MIS, Data Mining, OLAP, EIS
DSS ES
Intelligence Phase
Design Phase
GDSS, Management Science, ANN
Choice Phase
GDSS
Implementation Phase