Decision Theory and Decision Tree

Introduction to Decision Theory

• Decision making is an integral part of management
planning, organizing, controlling and motivation processes.
The decision maker selects one strategy (course of action)
over others depending on some criteria, like utility, sales,
cost or rate of return.

• Is used whenever an organization or an individual faces a

problem of decision making or dissatisfied with the
existing decisions or when alternative selection is
specified.
Elements related to all decisions
• Goals to be achieved: Objectives which the decision
maker wants to achieve by his actions
• The decision maker: Refers to an individual or an
organization
• Courses of action: Also called “Action” or “Decision
Alternatives”. They are under the control of decision
maker
• States of nature: Exhaustive list of possible future events.
Decision maker has no direct control over the occurrence
of particular event.
• Pay-off :Numerical value resulting from each pair of
possible combination of alternatives and states of nature
Steps in Decision Making
• Identify and define the problem
• List all future events called states of Nature
• Identify all course of action ( alternatives or
decision choices)
• Express the Pay-offs resulting from each
pair of course of action and states of
nature.
• Apply appropriate Decision theory model to
select the best course of action
Types of environment

• Decision making under certainty

• Decision making under risk
• Decision making under uncertainty
• Decision making under conflict (Game
Theory)
 Decision making under Certainty:
• There are certain problems wherein the decision maker is fully
equipped with the information and is well aware of all the facts
related to the states of nature.

• Besides, he has the knowledge of its occurrence as well. He is also

aware of the consequences of that state of nature. The problem of
decision making is simple in such situations.

• Thus, it is the selection of the strategy by the decision maker

which will yield maximum payoff, with respect to utility under the
state of nature whose occurrence is well known to him.
• In this case, the easy selection of the course of action by
the decision maker is a presumption, that only one state
of nature is purposeful.
• For example, for a certain period, a person is willing to
deposit 10000 rupees.
• The Post office offers 7.3% on Recurring deposit, Bank
offers 5.5% interest on Recurring deposit and
Government Bonds yields 5% interest p.a.
• Despite all the investments being fully secured,
investment in Post office is definitely best choice.
Decision making under certainty

• Decision maker has complete information

of consequences of every choice (course of
action)
• He will select the alternative that yields
highest payoff
• Eg: Decision to purchase NSC, Fixed deposit
etc
 Decision making under Risk

• Risk may be defined as the potential of losing

something of value.
• Values can be anything such as physical, health, social
status, emotional well-being or financial wealth.
• Whenever someone takes risks resulting from a given
action or activity then values can be gained or lost.
• In other words, risks can also be defined as the planned
interaction with uncertainty.
• Problems are linked with inventory level or
spare parts.
• Assigning of the probabilities to different states
of nature is possible on the basis of historical
data and past experience.
• Thus, in these cases the payoff matrix (player
has to make a choice without knowing what
choice the other will make) helps in arriving at an
excellent decision by assigning probabilities to
various states of nature.
• Various states of nature can be counted
under this condition as well as the long-
run frequency of them is supposed to be
known.
• Decision maker cannot predict about the
occurrence of outcome due to the result of
his selecting a particular course of action
as the information regarding the states of
nature is probabilistic.
Decision making under risk

• Decision maker has less than complete

information of consequences of every
choice (course of action)
• Eg: Probability of getting a head or tail
when a coin is tossed
1. Expected Monetary Value (EMV)

• EMV for the specified course of action is the weighted

average payoff ie. The sum of the product of the payoff for
the several combination of courses of action and states of
nature multiplied by the probability of occurrence of each
outcome.
 Decision making under Uncertainty
• Situation which contains the imperfect and unknown
information is known as Uncertainty.
• Uncertainty is generally used in different ways in different
fields like physics, statistics, economics, finance,
psychology and sociology.
• Uncertainty can be used to predict the future events to
physical measurements which is observed or to the
unknown.
• This situation arises generally due to indolence / laziness
and / or ignorance as well as in partially observable and
stochastic environments (random in nature which is not
unique – Ex Chess).
• If there is incomplete information available for a
decision environment, then the decisions taken
under such an environment are known as
Decision under Uncertainty.
• Then the information of the decision
environment, in such a situation is unable to be
explained in the form of probability
distribution.
 For Example
• while taking decisions related to new products,
packaging, promotional activities, prices and channel of
distribution, a marketing executive is challenged by
extraordinary situations.
• Some Influential factors such as product characteristics,
price, and the volume of sale effort can be structured by
the manger, but they must compete with the
uncertainties concerning factors like economic
conditions, taste of consumers and competitors .
Decision making under uncertainty
• Criterion of Pessimism or Maximin
• Criterion of Optimism or Maximax
 Decision under uncertainty:
There are several rules and techniques to take decision
under uncertainty situation. Important ones are shown in
the figure below:

Decision Choice Criteria

Maximax or Minimin Maximin or Minimax

Equally Likely Decision

Minimax Regret criteria

Criterion of Realism
 Decision making under Uncertainty
• Situation which contains the imperfect and unknown
information is known as Uncertainty.
• Uncertainty is generally used in different ways in different
fields like physics, statistics, economics, finance,
psychology and sociology.
• Uncertainty can be used to predict the future events to
physical measurements which is observed or to the
unknown.
• This situation arises generally due to indolence / laziness
and / or ignorance as well as in partially observable and
stochastic environments (random in nature which is not
unique – Ex Chess).
Maximax Or Minimin (Criterion of Optimism):

• According to criterion, it is ensured by the decision

maker to achieve maximum payoff or minimum cost
without missing the opportunity.

• Thus, he chooses a different course of action

represented by the maximum of the maxima or
minimum of the minima payoffs. The summary of the
working method is as follows:
1. Locating the payoff value (maximum or minimum) that
corresponds to each and every course of action.

2. Selection of an alternative, having the best expected payoff

value which maximise the profit and minimise the loss.

• This is called an optimistic decision criterion, due to the

selection of an alternative with highest/lowest available
payoff value by the decision maker.
Maximin Or Minimax (Criterion of Pessimism)

• According this criterion, it is ensured by the decision

maker that is earnings are not less than the specified
amount.
• Therefore, its selection of alternative is represented by
the maximum of the minima payoffs in the case of
profit, or minimum of the maxima in the case of loss.
• Summary of the working method is that follows-
1. Locate the pay of values both (minimum in the case of
loss and maximum in the case of profit) that
corresponding to each alternative
Decision Tree
• A decision tree is a decision support tool that uses a tree-
like graph or model of decisions and their possible
consequences, including chance event outcomes, resource
costs, and utility.
• It is one way to display an algorithm. Decision trees are
commonly used in operations research, specifically in
decision analysis, to help identify a strategy most likely to
reach a goal.
• Another use of decision trees is as a descriptive means for
calculating conditional probabilities. When the decisions
or consequences are modelled by computational verb,
then we call the decision tree a computational verb
decision tree
Introduction
• A decision Tree consists of 3 types of nodes:-
1. Decision nodes - commonly represented by
squares
2. Chance nodes - represented by circles
3. End nodes - represented by triangles
• a decision tree has only burst nodes (splitting
paths) but no merge nodes (converging paths).
 How to Draw a Decision Tree
• You start a Decision Tree with a decision
that you need to make.
• Draw a small square to represent this
towards the left of a large piece of paper.
• From this box draw out lines towards the
right for each possible solution, and write
that solution along the line.
• At the end of each line, consider the
results. If the result of taking that decision
is uncertain, draw a small circle. If the
result is another decision that you need to
make, draw another square. Write the
decision or factor above the square or
circle. If you have completed the solution
at the end of the line, just leave it blank.
• Keep on doing this until you have drawn
out as many of the possible outcomes and
decisions as you can see leading on from
the original decisions.
Thank You!
 B.N.M. Institute of Technology
OPERATIONS RESEARCH (22MBA24)
MODULE-1

1. Define Operations Research.

Operation Research is a systematic method-oriented study of basic structure, characteristics, functions and
relationship of an organization to provide the executive with some scientific and quantitative basis for
decision making.

2. List the scope of Operation Research?

The scope of operations research (OR) is vast and covers a wide range of industries and
applications.
• Production: OR can be used to optimize production schedules, determine the optimal size of a
production run, and allocate resources efficiently.
• Inventory: OR can be used to determine the optimal level of inventory, minimize stockouts, and
maximize profits.
• Transportation: OR can be used to find the most efficient way to transport goods or people,
minimize transportation costs, and meet demand requirements.
• Scheduling: OR can be used to develop optimal schedules for tasks, jobs, or projects, minimize
delays, and meet deadlines.
• Decision making: OR can be used to help managers make better decisions by providing them with
quantitative data and analysis.

3. What are the characteristics of Operations Research?

Characteristics of operations research (OR) are:

• System orientation: OR studies the problem as a whole, taking into account all the interrelated
factors. This is in contrast to traditional management methods, which often focus on individual
parts of a system.
• Mathematical modeling: OR uses mathematical models to represent real-world problems. This
allows OR practitioners to analyze the problem and identify potential solutions.
• Quantitative methods: OR uses quantitative methods to solve problems. This includes methods such
as linear programming, queuing theory, and game theory.
• Decision making: OR provides a systematic approach to decision making. This helps managers to
make better decisions in a more objective way.
• Interdisciplinary: OR is an interdisciplinary field that draws on a variety of disciplines, including
mathematics, statistics, economics, and computer science.
• Problem-solving: OR is a problem-solving tool that can be used to improve the efficiency and
effectiveness of organizations.
 B.N.M. Institute of Technology
4. What are advantages and limitations of Operations Research?

Advantages

• Improved decision making: OR provides a systematic approach to decision making that can help
managers to make better decisions in a more objective way.
• Increased efficiency: OR can be used to improve the efficiency of organizations by identifying and
eliminating waste.
• Reduced costs: OR can be used to reduce costs by finding ways to operate more efficiently.
• Improved productivity: OR can be used to improve productivity by finding ways to get more output
from the same amount of input.
• Better customer service: OR can be used to improve customer service by finding ways to meet
customer needs more effectively.
• Increased profits: OR can be used to increase profits by finding ways to reduce costs and improve
productivity

Limitations

• Data requirements: OR models require accurate and reliable data. If the data is not accurate, the
results of the model will be incorrect.
• Modelling assumptions: OR models make assumptions about the real world. If these assumptions
are not valid, the results of the model will be inaccurate.
• Complexity: OR models can be complex and difficult to understand. This can make it difficult to
communicate the results of the model to decision-makers.
• Cost: OR projects can be expensive. This can limit the use of OR in organizations with limited
resources.
• Acceptance: OR solutions may not be accepted by decision-makers. This can be due to a number of
factors, such as the complexity of the solution, the lack of understanding of the solution, or the fear
of change.

5. What are the models in Operation Research?

A model used in operation research is a representation of actual object or situation. It shows the
relationship between the action and reaction in terms of cause and effect.

Since a model is an abstraction of reality it is less complete than the actual. Therefore it is a representative
of those aspect that are being investigated the models can be classified based on the following
characteristics

• Classification by structure:
➢ Iconic model: Iconic model represents the system as it is by scaling up or scaling down.
o Example: Map, Globe, Picture.
➢ Analog model: Analog model is a model in which one set of properties are used to represent an
another set of properties.
o Example: A car takes 1hour to cover distance of 1Kilometer
 B.N.M. Institute of Technology
➢ Symbolic Model: Symbolic/Mathematical model is one which employs a set of mathematical
symbol to represent the decision variable of the system.
o Example: Straight line equation: y=a+bx

• Classification by purpose:
➢ Descriptive model: This model simply describes some aspects of situation.
o Example: it helps to describe the model.
➢ Predictive model: Predictive model are such models can answer “What if” type of questions.
o Example: with the facts we predicts the model.
➢ Prescriptive model: When a predictive model is repeatedly successful. Such model is used to
describe the solution.
o Example: When prediction is accurate, then it is prescriptive.

• Classification based on nature of environment:

➢ Deterministic model: Deterministic model are such model assume conditions with complete
certainty and perfect knowledge.
o Example: Determining outcome with great accuracy.
➢ Probabilistic model: This model usually handle situation in which the consequences cannot be
predicted with certainty.
o Example: prediction is not accurate.

• Classification by behaviour:
➢ Static model: These models do not consider the impact of changes that take place during the
planning.
o Example: No change with the time.
➢ Dynamic model: In this model times is considered as the most important variable and admit the
impact of changes generated by time.
o Example: Adapt changes with the time.

• Classification by method of solution

➢ Analog model: These models have specific mathematical structure and can be solved by
mathematically technique.
o Example: A toy train set is used to model the flow of traffic in a city.
➢ Simulation model: They also have mathematical structure but cannot be solved using tools and
techniques of mathematics only. It is essentially a computer assisted experimentation.
o Example: Weather forecasting.

6. Explain the Applications of Operations Research

• Finance and Accounting
➢ Dividend policies, investment and portfolio management, auditing, balance sheet and cash flow
analysis.
➢ Claim and complaint procedure, and public accounting.
➢ Break-even analysis, capital budgeting, cost allocation and control, and financial planning.
➢ Establishing costs for by-products and developing standard costs.
 B.N.M. Institute of Technology
• Marketing
➢ Selection of product-mix, marketing and export planning.
➢ Advertising, media planning, selection and effective packing alternatives.
➢ Sales effort allocation and assignment.
➢ Launching a new product at the best possible time.
➢ Predicting customer loyalty.

• Purchasing, Procurement and Exploration

➢ Optimal buying and reordering with or without price quantity discount.
➢ Transportation Planning
➢ Replacement policies
➢ Bidding policies
➢ Vendor analysis

• Production Management
➢ Facilitates Planning
➢ Location and size of warehouse or new plant, distribution centres and retail outlets.
➢ Logistics, layout and engineering design
➢ Transportation, planning and scheduling

• Manufacturing
➢ Aggregate production planning, assembly line, blending, purchasing and inventory control.
➢ Employment, training, layoffs and quality control
➢ Allocating R&D budgets most effectively

• Maintenance and project Scheduling

➢ Maintenance policies and preventive maintenance
➢ Maintenance crew size and scheduling
➢ Project scheduling and allocation of resources

• Personnel Management
➢ Manpower planning, wage/salary administration
➢ Designing organization structures more effectively
➢ Negotiation in a bargaining situation
➢ Skills and wages balancing

• Techniques and General Management

➢ Decision support systems and MIS; forecasting
➢ Making quality control more effective
➢ Project management and strategic planning

• Government
➢ Economic planning, natural resources, social planning and energy
➢ Urban and housing problems
➢ Military, police, pollution control, etc
 B.N.M. Institute of Technology
7. List and Explain the phases of OR

Following are the six phases and processes of operational research:

• Formulate the problem: This is the most important process, it is generally lengthy and time
consuming. The activities that constitute this step are visits, observations, research, etc.
With the help of such activities, the O.R. scientist gets sufficient information and support to
proceed and is better prepared to formulate the problem. This process starts with
understanding of the organizational climate, its objectives and expectations. Further, the
alternative courses of action are discovered in this step.
• Develop a model: Once a problem is formulated, the next step is to express the problem into
a mathematical model that represents systems, processes or environment in the form of
equations, relationships or formulas. We have to identify both the static and dynamic
structural elements, and device mathematical formulas to represent the interrelationships
among elements. The proposed model may be field tested and modified in order to work
under stated environmental constraints. A model may also be modified if the management is
not satisfied with the answer that it gives.
• Select appropriate data input: Garbage in and garbage out is a famous saying. No model will
work appropriately if data input is not appropriate. The purpose of this step is to have
sufficient input to operate and test the model.
• Solution of the model: After selecting the appropriate data input, the next step is to find a
solution. If the model is not behaving properly, then updating and modification is
considered at this stage.
• Validation/ Testing of the model: A model is said to be valid if it can provide a reliable
prediction of the system’s performance. A model must be applicable for a longer time and
can be updated from time to time taking into consideration the past, present and future
aspects of the problem.
• Implement the solution: The implementation of the solution involves so many behavioural issues and
the implementing authority is responsible for resolving these issues. The gap between one who
provides a solution and one who wishes to use it should be eliminated. To achieve this, O.R. scientist
as well as management should play a positive role. A properly implemented solution obtained
through O.R. techniques results in improved working and wins the management support.