HCS 410 DECISION SUPPORT SYSTEMS
CHAPTER 3: DECISION MAKING MODELS
3.1. ROLE OF MODELS IN DECISION MAKING
Models play an important role in decision making because:
A model is a simplified representation or abstraction of reality.
Models are usually simplified because reality is too complex to copy.
Analysis is performed on a model rather than on reality itself.
It may not be possible to experiment with real life systems due to
possible adverse effects.
It may be necessary to make simulations of different decision making
scenarios before implementing them in real life situations.
3.2. SIMON’S IDC MODEL OF DECISION MAKING
Herbert Simon is the Pioneer in the field of decision support systems (DSS)
by developing a model to enhance our understanding of the decision-making
process. His model of decision-making has three stages: Intelligence phase,
Design phase and the Choice phase.
3.2.1. Intelligence Phase
In this phase the decision-maker identifies/detects the problem or opportunity.
Problem is anything that is not happening according to the plan, rule or
standard. Opportunity seeking on the other hand is the identification of a
promising circumstance that might lead to better results. Thus, this phase
deals with the complete understanding of the problem/opportunity.
Intelligence phase of decision-making process involves: Problem
Searching: For searching the problem, the reality or actual is compared to
some standards. Differences are measured & the differences are evaluated to
1
determine whether there is any problem or not. Problem Formulation: When
the problem is identified, there is always a risk of solving the wrong problem.
In problem formulation, establishing relations with some problem solved
earlier or an analogy proves quite useful.
The DSS can be used to organise this captured information, generate timely
focused reports, and project trends. A computer can scan a large amount of
information to identify problems such as a decline in sales.
3.2.2. Design phase
Design phase consists of determining alternatives and evaluating them.
Models are also built simplify reality and explore alternative solutions. To
boost sales, several advertising proposals may be evaluated. A computerised
model that shows the cost of an advertising program and its expected effect
on sales can help a decision maker assess their potential. This phase requires a
lot of creativity and innovation to identify and develop design solutions.
3.2.3. Choice phase
Once alternatives are identified and their potential effect forecasted, a choice
can be made. Use a DSS or simulating the performance outcomes based on
the “what –IF” and goal seeking analysis. The computer can rank choices by
cost/benefit ratio, net benefit or any other desired criterion. The result of this
phase is a decision
3.3. Slade’s model
Slade’s model consist of the following phases
Identifying a problem
Identifying alternatives
Evaluating alternatives
Choosing among alternatives
Effecting the choice
Abandon the problem
2
Generate new alternatives
Choose usual action
Activity: In groups of 5s work on the following:
(a) Similarities between Simon’s model and Slade’s model
(b) Differences between the two models.
(c) The most important aspects of the two models.
(d) What are the strength and weaknesses of the Simon’s model and
Slade’s model.
(e) Critically evaluate Simon’s model and Slade’s model.
3.4. CLASSIFICATIONS OF MODELS
(a) Iconic models – Iconic (scale) models, the least abstract type, are
physical replicate of systems. It is usually based on a smaller scale
than the original. Examples: are models of aeroplanes, cars, bridges
or production lines
(b) Analog models An analogue model does not look like a real system,
but behaves like a real system. The shape of the model differs from
that of the actual system. Examples include Google maps or GIS
showing relief features and man-made objects.
(c) Mathematical/Quantitative models – Mathematical (quantitative)
models are the most abstract and may contain four types of
variables: result variables, decision variables, uncontrollable
variables and intermediate variables.
(d) Mental models – most abstract. People often use a behavioural
mental model which is an un-worded description of how people
think about a situation. The model can use the beliefs, assumptions,
relationships and flows of work as perceived by an individual. They
are a conceptual, internal representation used to generate
descriptions of problem structure and make future predictions of
related variables. Support for mental models is an important aspect
of Executive Information Systems.
3
3.5. ADVANTAGES OF MODELS
(a) The cost of modelling is much lower that the cost of experimentation
conducted with a real system
(b) Models allow for years of operation to be simulated in seconds of
computer time
(c) Manipulating the model is much easier than manipulating the real
system; models do not infer with the daily operations
(d) The cost of making errors during trial-and-error experimentation is
much lower when using models than the real system
(e) It is easier to access and manipulate a model when viewing alternatives
than applying alternative options to the real world
(f) A model compresses time and yields results more quickly than the real
world
