Computerized Decision Support

MODULE 2
COMPUTERIZED DECISION SUPPORT:

Researchers have identified a number of decision-making styles. These include heu-
ristic and analytic styles. One can also distinguish between autocratic versus democratic
styles. Another style is consultative (with individuals or groups). Of course, there are
many combinations and variations of styles. For example, a person can be analytic and
autocratic, or consultative (with individuals) and heuristic.
Web impact on the four phases is shown in the table:
Model: it is the simplified representation or abstraction of reality.
Descriptive models:
This model describe things as there are or they are believed to be. this models are
mathematically based.
Used in DSS for investigating the consequences of various alternative courses of action under
different configurations of inputs and process.
This will check the performance of the system for a given set of alternatives, there is no
gurantees that alternative selected is optimal.
Eg for descriptive model: simulation

Simulation is the imitation of reality and has been applied to many aera of decision making
Eg:computer video game, virtual reality
Common use of simulation is in manufacturing,to determine how to structure a website for
improved performance and to estimate future purchases.
Eg for nonmathematical descriptive model: cognitive map

cognitive map can help a decision maker sketch out the important qualitative factors and their
causal relationships in a messy decision making situation.this helps the decision marker focus
on what is relevant and what is not.
Software tool for cognitive mapping :Decision explorer
Good enough, or Satisficing:

When Satisficing, the decision maker sets up an aspiration,a goal or a desired level of
performance and then search the alternatives until one is found that achieves this level
Reasons for satisficing:
1. Time pressure
2. Ability to achieve optimization
3. Recognition that marginal benefit of a better solution is not worth the marginal cost to
obtain it
Satisficing is a form of subobtimization.
There may be a best solution,but it ould be difficult,if not impossible to attain it.
With normative model too much computation may be involved.
With descriptive model it may not be possible to evaluate all set of alternatives.
Risk:
All decision are made in an inherently unstable environment. this is due to the many
unpredictable events in both the economic and physical environments
Some risk may be arise due to internal organizational events
Eg: employee quitting or becoming ill
Due to natural disasters
Decision making:the choice phase
The choice phase is the one in which the actual decision and the commitment to follow a
certain course of action are made.
The choice phase include:
1. The search for evaluation: the choice can be evaluated as to their viability and
profitability.
2. Recommendation of appropriate solution to a model:
Solution to model is specific set of values for decision variable in a selected
alternatives
Solving the decision making involves searching for appropriate course of action
Search approach include:
1. Analytical technique: eg: solving formula
2. Algorithms eg: step by step procedures
3. Heuristic eg: rules of thumb
4. Blind searchs eg: shooting in dark
Each alternatives must be evaluated.if each alternatives have multiple goal ,they must all be
examined and balanced against each other.
Sensitivity analysis is used to determine the robustness of any given alternatives.
What-if analysis is used to explore major changes in the parameter
Decision making:the immplimentation phase
This phase involve putting a recommended solution to work, not necessarily implementing a
computer system.
Implementation issues are:
1.resistance to change
2. degree of support of top management
3. user training
Implimentation include the thorough understanding of project management.
Implementation involves collecting and analyzing data to learn from previous decisions and
improve the next decision.
Analysis of data is usually conducted to identify the problem and solution and analytics should
employed in the feedback process.
Data used for problem identification should be valid.
Quantitative models are made up of 4 components:

1. Result variables: these variable indicate how well the system performs or attains its goal.
These variables are the output
These are considered dependent variables
2. Decision variables:these variable describe alternative courses of action.
Decision marker controls the decision variable
Eg: for investment problem, the amount to invest in bonds is a decision variable
3. Uncontrollable variables or parameters:
In many decision making situation, there are factors that affect the result variable but
are not under the control of decision marker.
These variables can be fixed or varying.
Fixed factors are called uncontrollable variables or parameters.
Varying factors are called variables
Eg:interest rate
4. Intermediate result variables: these variables are sometimes used in modelling to identify
intermediate outcomes in mathematical model.
Eg: employee salary
It determine employee satisfaction.
The mathematical relationships link these components together.
The structure of mathematical models:
The components of a quatitative models are linked together by mathematical expressions.
The expressions are equations or inequalities
Simple financial model :
P=R-C
Where P=Profit
R=Revenue
C=Cost
This equation describe the relationship among the variables.
Based on decision marker knowledge about forecasted result decision situations are classified
into 3 categories, ranging from complete knowledge to complete ignorance:
1. Certainity
2. Risk
3. Uncertainity
Decision making under certainity:

In decision making under certainity, it is assumed that complete knowledge is available.
So that decision marker knows exactly what the outcome of each course of action
It may not true that the outcomes are 100% known, nor it is necessary to evaluate all the outcomes
.Decision marker is viewed as aperfect predictor because there is only one outcome for each
alternatives.
Eg: financial models are constructed under certainity.
Decision making under uncertainity:
In decision making under uncertainity , the decision marker consider situations in which several
outcomes are possible for each course of action.
It is more difficult than decision making under certainity because there is insufficient
information.
Managers attempt to avoid uncertainity as much as possible.
Instead of dealing with uncertainity, they attempt to obtain more information so that problem
can be treated under certainity or under calculated risk.
If more information is not available , the problem must e treated under a condition of
uncertainity.
Decision making under Risk(Risk analysis):

It is also known as probabilistic/stochastic decision making situation.
In this Decision marker must consider possible outcomes for each alternatives,each with given
probability of occurrence.
Decision marker can assess the degree of risk associated with each alternatives under the
assumption that outcomes will occur are assumed to be known or can be estimated
Risk analysis is a decision making method that analyzes the risk associated with different
alternatives.

Computerized Decision Support

Uploaded by

Copyright:

Available Formats

Computerized Decision Support

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Computerized Decision Support

Uploaded by

Copyright:

Available Formats

MODULE 2

COMPUTERIZED DECISION SUPPORT:

Eg for descriptive model: simulation

Eg for nonmathematical descriptive model: cognitive map

Good enough, or Satisficing:

Quantitative models are made up of 4 components:

Decision making under certainity:

Decision making under uncertainity:

Decision making under Risk(Risk analysis):

You might also like