The Modeling Phase

The Modeling Phase :
Bob & Jan can apply several solution approaches to the problem.
1. Trial & Error
2. Simulation
3. Optimization
4. Heuristics
 Trial & Error with Real System
In this approach, the owners try to learn from experimentation on the real
system.
Trial & error may not work if one or more of the following conditions exist.
o There are too many; alternatives to explore
o The cost of making errors is very high
o The environment keeps changing.

 Simulation
The technique of representing the real world by a computer program
Simulation, which is based on historical and projected data, can deal with
both situations.
The problem with the simulation approach is that once the experiment is
completed, there is no guarantee that the selected daily stocking level is
the best one.
 Optimization
Ideally such a model will generate an optimal order level in seconds.
For structured situation, there is very inexpensive and user friendly
software to conduct such an analysis.
Such a model will specify the required input data, the desired output, and
the mathematical relationship in a precise manner.
 Heuristics
The meaning of Heuristics - A commonsense rule (or set of rules)
intended to increase the probability of solving some problem


The Decision Making Process
1. Intelligence Phase
a) Finding the problem
b) Problem Classification
i) Programmed Problems
ii) Non programmed problems
c) Problem Decomposition
d) Problem Ownership
2. The Decision Phase
a) Components of Quantitative models
i) Result variables
ii) Decision variables
iii) Uncontrollable variables - Parameters
iv) Intermediate result variables
b) The structure of Quantitative models
c) Selection of a principle of choice
i) Normative models
ii) Sub Optimization
iii) Descriptive models
iv) Good enough or satisfying
d) Developing or generating alternatives
e) Predicting the outcome of each alternatives
i) Decision making under Certainty
ii) Decision making under Risk (Risk analysis)
iii) Decision making under uncertainty
f) Measuring outcomes
i) Scenarios
According to Simon – There are three phases for the decision making
process.
1 Intelligence Reality is examined & the problem is identified and defined.
2 Design A model that represents the system Is constructed.
3 Choice Includes a proposed solution to the model.
4 Implementation Once the proposed solution seems to be reasonable, it is ready
for the last phase.
 Intelligence Phase
Intelligence entails scanning the environment.
Finding the Problem
The intelligence phase begins with the identification of organizational
goals and objectives and determination of whether they are being met.
One attempts to determine whether a problem exists, identify its
symptoms, determine its magnitude, and explicitly define the problem.
The measurement of productivity and the construction of the model are
based on data.
Some issues that may arise during data collection and estimation are as
follow.
o Outcome may occur over an extended period of time. As a result,
revenues, expenses & profits will be recorded at different points of
time.
o It is often necessary to use a subjective approach to data
estimation.
o It is assumed that future data will be similar to historical data.