Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 51

Chapter-3

Modelling
Course Title: Decision Making

Course Instructor:

Dr. Adeel Raheem


Assistant Professor
Department of Business Administration
Preston University, Islamabad
Model
• A model is an explicit statement of our image of reality.
• It is a representation of the relevant aspects of the decision with which we
are concerned.
• It is the structuring and formalizing the information we posses about the
decision.
• Enhance the decision maker's understanding of the decision,
• Stimulate creativity in the search for possible solutions to the problem,
• Help in the evaluation of alternative courses of action.
Levels of Model
1. Descriptive Models
2. Analogue Models
3. Relationship Models
Descriptive Models
• The descriptive model simply explains certain aspects of the problem or
situation or a system so that the user can make use for his analysis.
• A descriptive model describes a system or other entity and its relationship to
its environment.
• It is generally used to help specify and/or understand what the system is,
what it does, and how it does it. 
• It includes what the observer perceived.
Analogue Models
Analogy:
• A comparison between one thing and another, typically for the purpose of
explanation or clarification.
• A correspondence or partial similarity.
• Thing which is comparable to something else in significant respects.
• For example, “Life is like a box of chocolates—you never know what
you're gonna get.”
…Analogue Models
Analogue Models:
• The next level in modelling is using analogy representing one set of
properties by another.
• Comparison of the observed situation with an analogous situation.
• Analogies rely on implication and association to describe the underlying
structure of a problem.
• They do not necessarily reveal the relationship between various elements.
• Example: contour lines in maps or graphical representation.
Relationship Models
• The most impartment part of understanding the problem with more clarity.

• In this level, model is being translated into more formal language, such as
mathematical symbols, words etc.
Uses of Modelling
Enhancing Understanding:

• A model can enhance our understanding of a decision.


• Acts as a vehicle for communication.
• Our understanding of the problem can be communicated to other decision
makers to share and improve.
Uses of Modelling
Stimulating Creativity:

• Once we have a statement of our perception of a problem, we have a vehicle


that is open to challenge and debate.
• Debate can help to open a door of new ideas.
• Totally new solutions can come up.
• Some mathematical models are specifically designed to explore the feasible
combination of decision variables and search out fresh solutions.
Uses of Modelling
Evaluating Alternatives:

• Model are used for evaluation of alternatives.


The Process of Modelling
The Process of Modelling
• A good model is one which reflects accurately our perception of the decision
area and can be used to aid the decision process.

• Prerequisites to the development of such model are the understanding of


variables within the decision, a knowledge of the influence between
variables, and a range of alternatives.
The Process of Modelling
Process of modeling involves following steps:

1. Classification of decision variables


2. Construction of cause-effect diagram
3. Major types of mathematical models in common use
4. Two alternatives to conventional mathematical modeling: heuristic modelling
and simulation modelling
5. Use of models to support corporate strategic decisions.
Step1: Classification of variables
• Variable is an element, feature, or factor that is liable to vary or change.
• Variable is something which is not constant.
• Example: Age, business income, expenses, capital expenditure, interest rate
etc.
• The opposite of variable is parameter which is assumed to have a constant
value over the period of time studied or the range of options considered.
• Sometimes many factors in the decision are variable in the reality, but are
treated as constant.
Cont..
Exogenous Variables:

• These are the independent inputs to the model which may be taken as acting
upon the decision.

• They can be either controllable or uncontrollable.

• Controllable exogenous variables are the inputs to the decision over


which the decision maker has influence. The values of controllable
exogenous variables are directly determined by the decision options.

• Uncontrollable exogenous variables are those which affect the decision


but are generated by the uncontrollable factors in the decision environment.
Cont..
Endogenous Variables:

• These are the dependent outputs to the model. They can be either
controllable or uncontrollable.

• Endogenous variables designates variables in a model that are explained, or


predicted, by independent variable.

• For example, the amount of crop yields is endogenous because it is


dependent on many other variables, such as the weather, soil fertility, water
availability, pests, and diseases.  
Step2: Cause-Effect Diagrams
• The simplest method of indicating that some relationship exists between two
factors with in a decision is to show the direction of influence by arrows on a
cause-effect diagram.
Cont..
Step3: Mathematical Models
• A symbolic model is one which uses any set of symbols to describe decision
variables and the relationship between them.
Operational Research
• “Operations Research” was coined during World War I. The British military
brought together a group of scientists to allocate insufficient resources — for
example, food, medics, weapons, troops, etc. — in the most effective way
possible to different military operations.
• So the term “operations” is from “military operations”. Successfully
conducting military operations was a huge deal and Operations Research
(OR) became its own academic discipline in universities in the 40s.
…Operational Research
• Operational research (OR) is a scientific approach to the solution of
problems in the management of complex systems that enables decision
makers to make better decisions.
• OR, is a discipline that deals with the development and application of
advanced analytical methods to improve decision-making.
• It is sometimes considered to be a subfield of mathematical sciences. 
• The benefits of OR can be a wide range of performance improvements
including cost reduction, revenue enhancement, saving lives, raising levels of
customer service or risk reduction.
…Operational Research
• The use of OR leads to more productive systems based on robust data
analysis, full consideration of available options, careful predictions of
outcomes and estimates of risk, and a collaborative approach that engages
with all stakeholder groups.

• Building quantitative models to support managers in their decision making is


the keystone of operational research.

1. Allocation Models
2. Queuing Models
3. Competitive Models
Allocation Models
• Allocation problems involve the distribution of resources among
competing alternatives in order to minimize total costs or maximize total
return.

• Allocation models can be created to present possible asset allocation


strategies for clients.

• A resource allocation model (RAM) is a methodology for determining where


resources should be allocated within an organization. Resources may
include financial resources, technological resources and human resources.
Queuing Models
• Queuing theory was developed by A.K. Erlang in 1904 to help determine the
capacity requirements of the Danish telephone system (Brockmeyer et al.
1948). It has since been applied to a large range of service industries
including banks, airlines, and telephone call centers as well as emergency
systems such as police patrol, fire and ambulances.

• Example in healthcare settings:


• Queuing models can be very useful in identifying appropriate levels of staff,
equipment, and beds as well as in making decisions about resource
allocation and the design of new services.
• Queuing theory aims to achieve a balance that is efficient and affordable.
Queuing Models
• Queuing model is a mathematical model which is constructed to predict
queue length and waiting time.
• As a branch of operations research, queuing theory can help inform business
decisions on how to build more efficient and cost-effective workflow systems.
• Queuing theory is the study of the movement of people, objects, or
information through a line.
• Often used as an operations management tool, queuing theory can address
staffing, scheduling, and customer service shortfalls.
Competitive Models
• Building quantitative models to support managers in their decision making is
the keystone of operational research.

• The Competitive Forces Model is an important tool used in strategic


analysis. The definition to analyze the competitiveness in an industry. 
Step4: Heuristic Models
• It originates from the ancient Greek word 'eurisko', meaning to 'find', 'search'
or 'discover'.
• The Heuristic method was, for the first time, coined by Dr. H. E. Armstrong
(1888-1928), Professor of Chemistry at City and Guild Institute Kensington. 
• It is about using a practical method that doesn’t necessarily need to be
perfect. Heuristic methods speed up the process of reaching a satisfactory
solution.
• Heuristic Models refers to techniques based on experience for various tasks
such as research, problem solving, discovery and learning.
• Heuristic methods enhance the pace of finding the desirable solution in
conditions where the comprehensive search is unfeasible.
Defining Heuristic Models
• Heuristics are rules-of-thumb that can be applied to guide decision-making
based on a more limited subset of the available information. Because they
rely on less information, heuristics are assumed to facilitate faster decision-
making than strategies that require more information.
• The heuristic approach adopts shortcuts in the reasoning process, and uses
rule of thumb in the search for a satisfactory solution.
• Sometimes uses trail and error method which is opposite to mathematical
model.
• There is no novelty in the use of heuristic decisions.
Example:
• Take a rain coat, if it looks weather is forecasted rainy.
• In stock market: Buy shares when the prices are low and expected to grow in
future.
Defining Heuristic Models
• Heuristics are generally more complex than these rules, but need not
necessarily be very much so.
• They are concerned to the satisfactory solution to be found, not optimization.
• Heuristic Programming: when a heuristic decision involves computation, to
select the option based on logical selection of computer based programming.
Usage of Heuristic Models
In two areas heuristic models are particularly useful when:

1. Where the decision is ill-structured and does not fit the assumptions of a
standard mathematical mode.

2. Where the range of feasible solution is so large that even modern


computing power does not allow complete enumeration.
…Cont
• The Heuristic Method only tries to find a good, but not necessarily optimal,
solution.
• This is what differentiates heuristics from exact solution methods, which are
about finding the optimal solution to a problem. However, that’s very time
consuming, which is why a heuristic method may prove preferable.
• This is much quicker and more flexible than an exact method, but does have
to satisfy a number of criteria.
• Heuristics are strategies that use readily accessible information for problem
solving in machines and human beings.
• Examples of such method include common sense, educated guess, or
intuitive judgment.
Heuristic Processing
• Heuristic processing employs the usage of judgmental rules called as
knowledge structures.
• These judgmental rules are learned and stored in memory with experience.
• The heuristic approach provides an economic advantage as it needs least
cognitive effort on the recipient’s part.
• Heuristic processing is governed by three factors including availability,
accessibility, and applicability.
• Availability is the presence of the knowledge structures or heuristics that
are stored in memory for futuristic purposes.
• Accessibility of the heuristic refers to the capability of retrieving the
memory for use.
• Applicability of the heuristic relies on how relevant are the knowledge
structures stored in memory to the judgmental task.
Heuristic Models
According of Polya, G (1945) there are many different heuristic methods:

1. Dividing technique
The original problem is divided into smaller sub-problems that can be solved
more easily. These sub-problems can be linked to each other and combined,
which will eventually lead to the solving of the original problem.

2. Inductive method
This involves a problem that has already been solved, but is smaller than the
original problem. Generalization can be derived from the previously solved
problem, which can help in solving the bigger, original problem.
Heuristic Models
3. Reduction method
Because problems are often larger than assumed and deal with different
causes and factors, this method sets limits for the problem in advance. This
reduces the leeway of the original problem, making it easier to solve.

4. Constructive method
This is about working on the problem step by step. The smallest solution is
seen as a victory and from that point consecutive steps are taken. This way,
the best choices keep being made, which will eventually lead to a successful
end result.

5. Local search method


This is about the search for the most attainable solution to the problem. This
solution is improved along the way. This method ends when improvement is
no longer possible.
Simulating Models
• All modelling is a simulation in as much as it imitates reality.
• The essence of simulation models is that they rely on a statement of
procedure which underlines the logical relationships between variables. It is
also called procedural models when the model is procedure expressed in
precise symbols.
• The term simulation actually refers to the method by which the model is used
to make predictions.
• A simulation model usually takes the form of a logical flowchart which
describes the interrelationship between variables.
• The model is then used to execute the procedure described in the flowchart.
Simulating Models
• Simulation explores the consequences of decision making rather than
directly advising on the decision itself.
• It is predictive rather than a optimizing technique.
• They are useful for predicting the dynamic behavior of systems.
• Simulation modeling solves real-world problems safely and efficiently. It
provides an important method of analysis which is easily verified,
communicated, and understood. Across industries and disciplines, simulation
modeling provides valuable solutions by giving clear insights into complex
systems.
Simulating Models
• Simulations allow for testing and experimentation in a more cost-effective
and/or safer environment. Using data gathered from the real world,
organizations, companies and individuals can create a virtual test to play out
ideas without having to waste physical resources or putting people’s lives at
risk.
• In other words, a simulation imitates how something has behaved previously,
presently and how it could behave in the future.
• However, it’s not a one size fits all: Everything in the world has a unique way
of operating therefore different types of simulation are required to allow for
various processes and systems to be modelled.
Corporate Modelling
• Some decisions are strategic whereas some decisions are operational.
• Corporate decisions are strategic in nature.
• For corporate decisions, we need corporate modelling.
• Corporate models are differ from other models, not necessarily by their
approach of modelling but by the nature of the variables involves in it.
Especially endogenous variables.
• Corporate strategic decisions involves considerations of a very wide range of
variables such as social, legal, technological and financial.
Corporate Modelling
Corporate modelling has come to mean:

• Models which use conventional “accounting” measures and relationships.


• Deterministic simulations representing a fairly “long time scale” such as
years rather than months.

• Indeed the process is sometimes called financial modelling rather than


corporate modelling.
• They measure the long term health of the organization. Examples: profit, net
cash, net present value, sales revenue.
Corporate Modelling Example
Model Classification
There are four dimensions to classify decision models:

1. Concrete or abstract
2. Normative or descriptive
3. Static or dynamic
4. Deterministic or stochastic
1.Concrete or Abstract
• A concrete noun refers to a physical object in the real world, such as a dog, a
ball, or an ice cream cone.
• An abstract noun refers to an idea or concept that does not exist in the real
world and cannot be touched, like freedom, sadness, or permission.
• This classification refers to the degree of correspondence with reality that a
model possesses.
• Concrete thinking refers to the thinking on the surface whereas abstract
thinking is related to thinking in depth.
Comparison Table Between Concrete Thinking and Abstract Thinking

Parameters of
Concrete Thinking Abstract Thinking
Comparison

Concrete thinking refers to the


Abstract thinking is the process of
Definition process of thinking about physical
thinking deeply about abstract ideas.
things from the surface level.

Abstract ideas such as emotions like


Ideas relating to the survival instinct
Ideas involved love, anger, hatred are involved in
are involved.
abstract thinking.

Thinking involves only the surface


Level of thinking A deep level of thinking is involved.
level.

This type of thinking occurs during This type of thinking occurs during
Scenarios
the assessment of the surroundings. important decision making.

Pace of thinking Quick thinking is performed. This is a time-consuming process.


2. Normative or Descriptive
• Descriptive: What people actually do, or have done.
• Prescriptive: What people should and can do.
• Normative: What people should do (in theory).

• A descriptive statement gives an account of how the world is without


saying whether that's good or bad.
• A normative statement expresses an evaluation, saying that something
is good or bad, better or worse, relative to some standard or alternative.
2. Normative or Descriptive
• Normative models attempt to impose on the decision maker the values
reflected in the assumptions of the model.
• They are more dominant in the model purely descriptive models, since they
assume responsibility for the direct evaluation of feasible solutions.
• Normative model do not necessarily optimized.
• Heuristic models are normative models.
2. Normative or Descriptive
• Descriptive models do not attempt to evaluate alternative decision
solutions, they merely describe them.
• This does not mean that they lack value, they can support understanding
and predict future behavior.
• They perform the first step in evaluation process by stating different feasible
decision solutions.
3. Static or Dynamic
• Static models where time is not a significant variable.
• Dynamic Models focusing on the evolution of the system under investigation
over time.
4. Deterministic or Stochastic
• A deterministic model is one that uses numbers as inputs, and produces
numbers as outputs.
• A stochastic model includes a random component that uses a distribution as
one of the inputs, and results in a distribution for the output.
• A stochastic model represents a situation where uncertainty is present. In
other words, it’s a model for a process that has some kind of randomness. 
• The word stochastic comes from the Greek word stokhazesthai meaning to
aim or guess.
• In the real word, uncertainty is a part of everyday life, so a stochastic model
could literally represent anything.
4. Deterministic or Stochastic
• The opposite of stochastic is a deterministic model, which predicts outcomes
with 100% certainty.
• Deterministic models always have a set of equations that describe the
system inputs and outputs exactly.
• On the other hand, stochastic models will likely produce different results
every time the model is run.

All stochastic models have the following in common:


• They reflect all aspects of the problem being studied,
• Probabilities are assigned to events within the model,
• Those probabilities can be used to make predictions or supply other
relevant information about the process.
My dear students and
learners,
Wish you all to become
future leaders and a good
decision maker in your
personal and corporate
life.

Thank
Contact Details:
You
Dr. Adeel Raheem
adeelraheem1@gmail.com

You might also like