QUANTITATIVE TECHNIQUE

1. Explain Bellman's principles of optimality.

Bellman's principle of optimality is a fundamental concept in the field of dynamic
programming and plays a crucial role in solving optimization problems, especially those
related to sequential decision-making under uncertainty.
Formulated by mathematician Richard Bellman, this principle essentially states that an
optimal policy has the property that, whatever the initial state and initial decisions are, the
remaining decisions must constitute an optimal policy with regard to the state resulting from
the first decision.
In simpler terms, the principle can be summarized as follows:
"An optimal policy has the property that whatever the initial state and initial decisions are,
the remaining decisions must constitute an optimal policy with regard to the state resulting
from the first decision."

2. What are the assumptions made in theory of games?

 Rationality: Game theory assumes that all players are rational, meaning they make
decisions that maximize their own utility or payoff based on their preferences and
available information. Rationality doesn't necessarily imply perfect decision-making
but assumes that players act in a way that's consistent with their preferences.
 Complete information or common knowledge: In some game models, it's assumed
that all players have complete information about the game, including the rules,
payoffs, strategies available to other players, and past actions. Additionally, there's a
presumption of "common knowledge," where each player knows the game structure
and knows that every other player knows it too, and so on.
 Static vs. dynamic games: Game theory often distinguishes between static (or
simultaneous-move) and dynamic (or sequential-move) games. Static games assume
that all players make decisions simultaneously without knowing the actions of
others. Dynamic games involve sequential moves, where players take turns making
decisions, potentially observing previous players' choices.
 Zero-sum vs. non-zero-sum games: Zero-sum games are situations where the total
payoff is constant, meaning any gain by one player is exactly balanced by losses of
others. Non-zero-sum games allow for situations where outcomes aren't strictly
opposing (i.e., cooperative or competitive), and gains or losses can be unevenly
distributed among players.
 Perfect information and perfect foresight: Some models assume that players have
perfect information about the game, including the outcomes of all possible actions.
 Similarly, perfect foresight assumes that players can accurately predict future actions
and their consequences.
 No externalities: Game theory often assumes that decisions made by one player do
not affect other players outside the framework of the game. Externalities, such as
side effects or impacts on other individuals or systems not involved in the game
directly, are typically excluded.

3. Advantage of using linear programming.

 Versatility: Linear programming is a versatile tool used in various fields, including

economics, engineering, operations research, finance, and business management. It
can solve a wide range of optimization problems, such as resource allocation,
production planning, transportation logistics, scheduling, and more.
 Optimization: LP helps in maximizing or minimizing a linear objective function while
considering multiple constraints. This allows finding the best possible solution given
the limitations imposed by constraints.
 Efficiency: LP algorithms are efficient and can find optimal solutions for moderately
large problems in a reasonable amount of time. Various algorithms, such as the
Simplex method or interior-point methods, efficiently handle different types of linear
programming problems.
 Mathematical Rigor: LP provides a mathematically rigorous framework for modelling
and solving optimization problems. It uses linear relationships, which simplifies the
modelling process and allows for clear interpretations of the results.
 Sensitivity Analysis: LP allows for sensitivity analysis, which examines how changes
in parameters or constraints affect the optimal solution. This helps in understanding
the robustness of the solution to changes in the input data.
 Decision Support: LP can provide decision support by analysing various scenarios and
recommending optimal decisions. This is particularly useful in business decision-
making, where it helps in resource allocation, cost minimization, profit maximization,
and strategic planning.
 Graphical Interpretation: In certain cases, with two decision variables, LP problems
can be graphically represented, making it easier to understand the feasible region,
constraints, and optimal solutions.
 Software Availability: Numerous software tools and libraries are available that
facilitate solving linear programming problems. These tools offer user-friendly
interfaces and allow solving complex problems efficiently.

4. Describe the transportation problem with its general mathematical formulation.

The transportation problem is a classic optimization problem in operations research and
logistics that involves minimizing the cost of transporting goods from multiple sources to
multiple destinations.
In a transportation problem scenario, there are:

 Sources (e.g., factories, warehouses): Locations where goods are available for
shipment.
 Destinations (e.g., retailers, customers): Locations where goods need to be
delivered.
 Supply: The amount of goods available at each source.
 Demand: The amount of goods required at each destination.
 Costs: The cost associated with shipping goods from each source to each destination.
The goal is to determine the optimal shipment quantities from sources to destinations in a
way that minimizes total transportation costs while satisfying supply and demand
constraints.
Mathematically, the transportation problem can be formulated as follows:
 Decision Variables: Let xij represent the quantity of goods shipped from source i to
destination j.
 Parameters:
si: Supply available at source i.
dj: Demand required at destination j.

cij: Cost of shipping one unit of goods from source i to destination �j.
 Objective Function: Minimize the total transportation cost.
Minimize ∑∑cij⋅xij
 Constraints:
Supply Constraints: Ensure that the total amount shipped from each source does not exceed
the available supply.
Demand Constraints: Ensure that the total amount received at each destination meets the
demand.
Non-Negativity Constraints: Ensure that shipment quantities are non-negative.

5. What is Hungarian method?

The Hungarian Method is an algorithm used to solve the assignment problem, which is a
specific type of optimization problem in operations research. The assignment problem deals
with finding the optimal assignment of a set of tasks (jobs) to a set of agents (workers) in
such a way that minimizes the total cost or maximizes the total profit.
The Hungarian Method is particularly efficient in finding the optimal solution for square cost
matrices (i.e., the number of rows equals the number of columns) where each row
represents a task and each column represents an agent, and the elements in the matrix
denote the cost of assigning a particular task to a specific agent.

6. What is payoff matrix?

A payoff matrix is a tool used in game theory to represent the possible outcomes of a
strategic interaction between two or more decision-making entities, often referred to as
players or agents. It outlines the payoffs or outcomes associated with various combinations
of choices made by the players involved in the game.
In a payoff matrix:
 Each row typically represents the possible strategies or actions available to one
player, while each column represents the possible strategies or actions available to
another player.
 The cells within the matrix display the respective payoffs or outcomes to each player
resulting from the combination of strategies chosen by both players.
Payoff matrices are commonly used in various game theory models, such as the
prisoner's dilemma, the Battle of the Sexes, the stag hunt, and other strategic
interaction scenarios. The entries in the matrix could represent different outcomes,
such as monetary rewards, utility, points, or any other measure of benefit or loss
relevant to the specific context of the game.

7. What are restrictions on assignment?

Restrictions or constraints on assignment refer to limitations or conditions that must be
satisfied when assigning tasks to agents or resources in an optimization problem. These
constraints are often present in various assignment problems, such as the assignment
problem in operations research or resource allocation scenarios, and they impose
restrictions on how tasks or jobs can be assigned to agents or resources.
Some common restrictions on assignment include:

 Capacity Constraints
 Precedence Constraints
 Exclusivity Constraints
 Availability Constraints
 Skill or Qualification Constraints
 Geographical Constraints
 Budget Constraints
 Mutual Exclusivity Constraints

8. What is C.P.M? Explain the following:

a) Total Float
b) Free Float
c) Independent Float
d) Slack
e) Activity
CPM stands for Critical Path Method, which is a project management technique used to plan
and manage complex projects by analysing the sequence of activities, their durations,
dependencies, and the critical path. It helps in scheduling project activities to determine the
shortest possible duration to complete the project.
In summary, in the Critical Path Method (CPM):

 Total Float measures the flexibility in the entire project schedule without delaying
the project completion.
 Free Float assesses the flexibility within an activity without delaying its succeeding
activities.
 Independent Float considers the maximum delay an activity can have without
affecting immediate succeeding activities that share a common predecessor.
 Slack or Float denotes the available time an activity can be delayed without
impacting the project's overall schedule.
 Activities are the individual tasks or work elements within a project, each with its
own duration, dependencies, and impact on the project's schedule.

9. Briefly explain steps involved in LPP method.

Linear Programming (LP) is a mathematical method used for optimizing a linear objective
function subject to a set of linear equality and/or inequality constraints. The steps involved
in solving a Linear Programming problem typically include:

 Formulation of the Objective Function

 Identification of Decision Variables
 Setting up Constraints
 Graphical Representation (for two variables)
 Formulation of the Standard Form
 Application of LP Algorithms
 Interpretation of Results
 Sensitivity Analysis (Optional)
These steps serve as a general guideline for solving linear programming problems. The
specific methodology and techniques employed may vary based on the problem's
complexity, the number of variables and constraints, and the chosen optimization algorithm.

10. Explain the procedure of resolving degeneracy in LPP.

Degeneracy in Linear Programming (LP) occurs when the basic feasible solution of the LP
problem has one or more basic variables that are zero. It can lead to issues with certain
solution methods like the Simplex algorithm, causing inefficiencies or cycling in finding the
optimal solution. Resolving degeneracy involves specific techniques aimed at overcoming
these issues to efficiently solve the LP problem.
Here are some procedures commonly used to resolve degeneracy in Linear Programming:

 Perturbing the Objective Function Coefficients

 Choosing the Entering Variable Carefully
 Using the Two-Phase Simplex Method
 Anti-Cycling Techniques
 Advanced Linear Programming Algorithms
Resolving degeneracy in Linear Programming often involves a combination of these
techniques and selecting the most appropriate approach based on the specific
characteristics of the problem. It's important to note that while these methods help in
mitigating degeneracy, in some cases, degeneracy might still persist, and additional
strategies may be required to achieve an optimal solution efficiently.

11. What is transportation problem and features of transportation problem.

The transportation problem is a specific type of linear programming problem commonly
encountered in logistics, supply chain management, and operations research. It involves
minimizing transportation costs while meeting the demand for goods from multiple sources
to multiple destinations. Here are the key features of the transportation problem:

 Sources and Destinations

 Supply and Demand
 Costs or Transportation Matrix
 Objective Function
 Decision Variables
 Constraints
 Feasible Solutions
 Optimality Criteria
 Degeneracy
 Solution Methods

12. Differentiate between transportation and assignment problem.

13. Define network analysis and explain three functions of network scheduling.
Network analysis, also known as network scheduling or project network analysis, is a
technique used in project management to visualize and analyse the flow of activities, their
interdependencies, and the critical path within a project. It involves representing project
tasks or activities as nodes connected by arrows (representing dependencies) to form a
network diagram.
Three functions of network scheduling in project management are:

 Visualization and Planning: Network scheduling helps in visualizing the sequence of

activities and their relationships within a project. By creating a network diagram
(such as a PERT chart or a CPM diagram), project managers can see the order in
which activities must be completed and the dependencies between tasks. This
visualization aids in better planning and organizing the workflow, allowing project
teams to understand the project's structure and critical path.

 Determining Critical Path: One of the key functions of network scheduling is to

identify the critical path in a project. The critical path represents the sequence of
tasks that, if delayed, would directly impact the project's overall duration. By
analysing the network diagram, project managers can determine the critical path,
which helps in focusing resources and attention on the most critical activities to
ensure the project is completed on time.

 Time and Resource Management: Network scheduling assists in time management

by estimating the duration of the project based on the sequence of activities and
their dependencies. It allows for better resource allocation by identifying activities
that require more time or resources, enabling project managers to allocate resources
efficiently and manage the project timeline effectively. Additionally, it helps in
identifying activities with float or slack, which can be adjusted to optimize resource
utilization.

14. Discuss the concept of decision making under uncertainty.

Decision-making under uncertainty refers to the process of making choices when the
outcomes of those choices are uncertain or not fully known. In real-world situations,
uncertainty is common due to incomplete information, variability, unpredictability, and the
presence of multiple possible outcomes or scenarios.
Key aspects and concepts related to decision-making under uncertainty include:

 Incomplete Information
 Risk and Uncertainty
 Probability and Subjective Assessment
 Decision-Making Models
 Risk Management and Mitigation Strategies
 Flexibility and Adaptability
 Decision-Making Heuristics
 Scenario Planning and Sensitivity Analysis

15. What is game theory? Explain types of game theory.

Game theory is a branch of applied mathematics and economics that studies strategic
interactions between rational decision-makers (known as players) in situations where the
outcome of a player's choice depends not only on their own actions but also on the actions
of others. It provides a framework for analysing and understanding the behaviour of
individuals or entities in competitive or cooperative situations.
Key elements of game theory include:

 Players: Individuals, entities, or agents involved in the game, each making choices
that affect the outcomes.
 Strategies: Courses of action available to each player, representing their decisions or
choices.
 Payoffs or Outcomes: The consequences or rewards associated with different
combinations of strategies chosen by the players.
 Information: Whether players have completed or incomplete information about the
game, their opponents' strategies, and the possible outcomes.
Types of game theory:

 Cooperative Game Theory:

 Non-Cooperative Game Theory:
o Normal Form Games (Static Games):
o Extensive Form Games (Sequential Games):
o Repeated Games:

16. Write a short note on the following:

 a) PERT
b) Dominance rule
c) Fulkerson's rule
Certainly! Here are short notes on each of the topics:

PERT (Program Evaluation and Review Technique):

PERT is a project management tool used for scheduling, organizing, and coordinating tasks
within a project. It helps in planning the timeline of activities by analysing the time required
for each task and their interdependencies. PERT uses three time estimates for each task:
optimistic time (the minimum time required), pessimistic time (the maximum time
required), and most likely time. By considering these estimates, PERT calculates the
expected time for each task, identifies the critical path (sequence of tasks that determine
the project's duration), and helps in managing uncertainties and risks associated with project
completion timelines.

Dominance Rule:
In the context of decision-making, the dominance rule is a principle used to compare and
evaluate alternatives by eliminating inferior or dominated options. An alternative is said to
be dominated when there exists another alternative that is at least as good in all respects
and strictly better in at least one aspect. According to the dominance rule, dominated
alternatives can be eliminated from consideration as they offer no advantage over other
available options. By applying this rule, decision-makers can simplify complex decision
problems by focusing on superior alternatives and reducing the number of choices to
consider.

Fulkerson's Rule:
Fulkerson's Rule is a method used in network flow problems to find a feasible flow solution
in a network with integer capacities. Specifically, it is applied in the context of the Ford-
Fulkerson algorithm for solving maximum flow problems. Fulkerson's Rule suggests that if all
capacities in a network are integers, there exists an integral maximum flow solution. It
implies that when the capacities in a network are integers, the Ford-Fulkerson algorithm can
be used to find the maximum flow, and the resulting flow values on each edge will also be
integers.

17. Steps of Hungarian method.

Step 1: Prepare the Cost Matrix:

 If the matrix is not a square matrix (number of rows ≠ number of columns), add
dummy rows or columns to make it square.
 Convert the matrix of costs to a matrix of equivalent opportunity costs by finding the
largest value in the matrix and subtracting it from every element.
Step 2: Initial Assignment:

 Start with an initial assignment by marking the rows and columns to create a
minimum number of lines (zeroes) that cover all zeroes in the matrix. These lines can
be horizontal or vertical.
Step 3: Covering Zeroes:

 Cover as many zeroes as possible with the minimum number of lines while ensuring
that each row and column has at least one zero covered. This step aims to identify
potential assignments and reduce the matrix size.
Step 4: Finding Minimum Number of Lines:

 If the number of lines drawn is equal to the matrix's size (n lines for an n x n matrix),
an optimal assignment is achieved, and the algorithm proceeds to Step 6.
 If the number of lines is less than n, proceed to Step 5.
Step 5: Modify the Matrix:

 Determine the smallest element not covered by any line (let it be m).
 Subtract m from every uncovered element and add m to every element that is
covered by two lines. Return to Step 3.
Step 6: Obtain the Assignment:

 Interpret the resulting matrix to obtain the assignment of tasks to agents that
minimizes the total cost or maximizes the total profit. Identify the assignments where
each task is assigned to exactly one agent and vice versa.
Step 7: Iterative Improvement (Optional):

 Depending on the problem's complexity, you might need to perform iterative

improvements by unassigning and reassigning tasks based on new line coverings to
achieve an optimal assignment.
 18. Describe various types of Simulation and also explain steps of Monte-Carlo
technique.
Simulation is a technique used to model and analyse real-world systems or processes by
imitating their behaviour through the creation of computer-based models. It involves
generating artificial environments or scenarios to study the performance or behaviour of a
system under different conditions. There are various types of simulations, each designed for
specific purposes:
1. Discrete Event Simulation:
 Discrete event simulation focuses on modelling systems where events occur
at distinct points in time. It involves modelling and tracking changes in the
system's state based on events that trigger state transitions. Examples include
computer systems, manufacturing processes, and queuing systems.
2. Continuous Simulation:
 Continuous simulation deals with systems that change continuously over
time. It involves modelling dynamic systems with continuous variables and
differential equations. Examples include physical systems like fluid flow,
chemical reactions, or economic models.
3. Agent-Based Simulation:
 Agent-based simulation models individual agents or entities with specific
behaviours and interactions within a system. Agents interact with each other
and the environment, leading to emergent system behaviour. Examples
include social simulations, traffic simulations, and ecological models.
4. Monte Carlo Simulation:
 Monte Carlo simulation involves random sampling techniques to model and
simulate uncertainties in a system. It generates multiple random scenarios
and analyses their outcomes to estimate probabilities or make predictions.
Steps of Monte Carlo Simulation:
1. Problem Definition:
 Clearly define the problem to be simulated, including the variables,
assumptions, constraints, and the system's behaviour to be modelled.
2. Identify Parameters and Distributions:
 Determine the input parameters that affect the system and their probability
distributions. These parameters could represent uncertainties, such as
demand, cost, or time.
3. Generate Random Samples:
 Generate random samples or values for the input parameters based on their
probability distributions. Use random number generators to simulate
different scenarios.
4. Perform Simulations:
 Run the simulations by plugging the random values into the model or system
to observe how the system behaves under each set of input parameters.
5. Analyse Results:
 Analyse the results obtained from the simulations. Collect data on system
performance, outcomes, or key metrics of interest across multiple simulation
runs.
6. Draw Conclusions:
 Draw conclusions based on the analysis of simulation results. Use statistical
techniques to estimate probabilities, forecast outcomes, or evaluate the
system's behaviour under different scenarios.
Monte Carlo simulation is widely used in finance, engineering, risk assessment, project
management, and many other fields to assess uncertainties and make informed decisions in
complex systems where deterministic modelling is impractical or impossible.