Montecarlo Simulation

Unit 1

PART IV
Simulation Introduction
• Simulation is a technique of solving decision making problem by
designing constructing and manipulating a model of real system. To
find out how the real process would react to certain changes, we can
produce this changes in our model and simulate the reaction of the
real process to them. In simulation we build mathematical models
which we cannot solve and run them and sample data to simulate the
behaviour of the system.
• designing a model of real system.
Simulation Introduction
The reason why management expert use simulation to solve management
problems are :
1) It may be the only method available because it is difficult to observe the
actual environment
2) It is not possible to develop mathematical solution
3) Actual observations of team may be two expensive
4) Sufficient time is not available to allow the system to operate extensively
5) Actual operations and observation of system maybe different
along with the advantages of using simulation technique there are some
limitations of simulation
Limitations:
1) It is not precise
2) It does not generate optimal solutions to problem as the other
quantitative techniques do
3) Sometimes developing a model is a time consuming long process
4) Simulation model does not produce answers by itself
5) All situations cannot be valuated using simulation only situations
involving uncertainty can be used for simulation
Simulation Process
Simulation process the simulation method is also called Monte Carlo
method following are the steps we generally follow
1) Define the problem or system to be simulated
2) Formulate the model
3) Test the model compare its behaviour with the behaviour of actual
problem. Identify and collect the data needed to test the model
4) Run the simulation
5) Analyse the results of the simulation and if required change the
solution to be valuated
6) Return the simulation for new solution
7) Validate the simulation
Introduction
• Risk analysis is part of every decision we make. We are constantly
faced with uncertainty, ambiguity, and variability. And even though
we have unprecedented access to information, we can’t accurately
predict the future. Monte Carlo simulation (also known as the Monte
Carlo Method) lets you see all the possible outcomes of your
decisions and assess the impact of risk, allowing for better decision
making under uncertainty

• Source : https://www.palisade.com/risk/monte_carlo_simulation.asp
Monte Carlo Simulation - Introduction
• Monte Carlo Simulation, also known as the Monte Carlo Method
or a multiple probability simulation, is a mathematical technique,
which is used to estimate the possible outcomes of an
uncertain event.
• The Monte Carlo Method was invented by John von Neumann and
Stanislaw Ulam during World War II to improve decision making under
uncertain conditions. It was named after a well-known casino town,
called Monaco, since the element of chance is core to the modelling
approach, similar to a game of roulette.
Monte Carlo Simulation
• Since its introduction, Monte Carlo Simulations have assessed the
impact of risk in many real-life scenarios, such as in artificial
intelligence, stock prices, sales forecasting, project management, and
pricing.
• Monte Carlo simulation furnishes the decision-maker with a range of
possible outcomes and the probabilities they will occur for any choice
of action. It shows the extreme possibilities—the outcomes of going
for broke and for the most conservative decision—along with all
possible consequences for middle-of-the-road decisions.
Monte-Carlo methods/Simulations:
• have been invented in the context of the development of the atomic
bomb in the 1940’s
• are a class of computational algorithms
• can be applied to vast ranges of problems
• are not a statistical tool
• rely on repeated random sampling
• provide generally approximate solutions
• are used in cases where analytical or numerical solutions don’t exist
or are too difficult to implement
How Monte Carlo Simulation
Works
• Monte Carlo simulation performs risk analysis by building models of
possible results by substituting a range of values—a probability
distribution—for any factor that has inherent uncertainty. It then
calculates results over and over, each time using a different set of
random values from the probability functions. Depending upon the
number of uncertainties and the ranges specified for them, a Monte
Carlo simulation could involve thousands or tens of thousands of
recalculations before it is complete. Monte Carlo simulation produces
distributions of possible outcome values.
• By using probability distributions, variables can have different probabilities
of different outcomes occurring. Probability distributions are a much more
realistic way of describing uncertainty in variables of a risk analysis.
• Common probability distributions include:
Normal
Lognormal
Uniform
Triangular
PERT
Discrete
• Normal Distribution:
Or “bell curve.” The user simply defines the mean or expected value
and a standard deviation to describe the variation about the mean.
Values in the middle near the mean are most likely to occur. It is
symmetric and describes many natural phenomena such as people’s
heights. Examples of variables described by normal distributions
include inflation rates and energy prices.
• Lognormal :
Values are positively skewed, not symmetric like a normal distribution.
It is used to represent values that don’t go below zero but have
unlimited positive potential. Examples of variables described by
lognormal distributions include real estate property values, stock
prices, and oil reserves.
• Uniform:
All values have an equal chance of occurring, and the user simply defines
the minimum and maximum. Examples of variables that could be
uniformly distributed include manufacturing costs or future sales
revenues for a new product.
• Triangular:
The user defines the minimum, most likely, and maximum
values. Values around the most likely are more likely to occur.
Variables that could be described by a triangular distribution include past
sales history per unit of time and inventory levels.
• PERT:
The user defines the minimum, most likely, and maximum values, just like the
triangular distribution. Values around the most likely are more likely to occur.
However values between the most likely and extremes are more likely to occur
than the triangular; that is, the extremes are not as emphasized. An example of
the use of a PERT distribution is to describe the duration of a task in a project
management model.
• Discrete:
The user defines specific values that may occur and the likelihood of each. An
example might be the results of a lawsuit: 20% chance of positive verdict, 30%
change of negative verdict, 40% chance of settlement, and 10% chance of
mistrial.
• During a Monte Carlo simulation, values are sampled at random from
the input probability distributions. Each set of samples is called an
iteration, and the resulting outcome from that sample is recorded.
Monte Carlo simulation does this hundreds or thousands of times,
and the result is a probability distribution of possible outcomes. In
this way, Monte Carlo simulation provides a much more
comprehensive view of what may happen. It tells you not only what
could happen, but how likely it is to happen.
Steps of Monte Carlo Simulation
• The Monte Carlo simulation technique consists of following steps
1 Setting up a probability distribution for variables to be analysed
2 Building cumulative probability distribution for each random variable
3 Generate random numbers assign an appropriate set of random
numbers to represent value for range (interval) of values for each random
variable
4 Conduct the simulation experiment by means of random sampling
5 Repeat step 4 until than required number of simulation runs has been
generated
6 design and implement a course of action and maintain control
Simulation – What it is /not

It is It is not
• A technique which uses computers. • An analytical technique which
• An approach for reproducing the provides exact solution
processes by which events of • A programming language but it
chance and change are created in a could be programmed into a set
computer
of commands which can form a
• A procedure for testing and language to facilitate the
experimenting on models to answer programming of simulation
what if ….. Then so and so… types
of questions
Example
• A bakery keeps stock of popular brand of cake daily demand based on
past experience given below :
Daily Demand 0 15 25 35 45 50
Probability 0.01 0.15 0.20 0.50 0.12 0.02
• consider the following sequence of random numbers 48,78, 09,51,
56,77, 15, 14, 68 and 9
i) using the sequence simulate the demand for the next 10 days
ii) find the stock situation if the owner of the bakery decide to make
35 cakes everyday also estimate the daily average demand for the
cakes on the basis of the simulated data
Solution: a) The simulated demand
for cakes for next 10 days is shown
in table
Demand Probability Cumulative Probability Random Number Interval
0 0.01 0.01 begin with 0 00 – 00 (Cp-1)
15 0.15 0.16 (Last CP) 01-15 (CP-1)
25 0.20 0.36 (Last CP) 16-35 (CP-1)
35 0.50 0.86 (Last CP) 36-85(CP-1)
45 0.12 0.98 (Last CP) 86-97(CP-1)
50 0.02 1.00 (Last CP) 98-99(CP-1)

Random 48 78 09 51 56 77 15 14 68 09
Number
Daily 35 35 15 35 35 35 15 15 35 15
Demand
• Each random number represents sample of demand.
Thus the number 00 is assigned to zero demand, the
numbers 9,15,14 and 9 are assigned to demand of 15
cakes, 16-35 are assigned to demand of 25 cakes and
so on. These random numbers give the demand for
cakes for next 10 days
b) The stock situation for various days if the
decision is made to make 35 cakes every day
shown inDays
table
Demand Number of cakes made Stock
1 35 35 0
2 35 35 0
3 15 35 20
4 35 35 20
5 35 35 20
6 35 35 20
7 15 35 40
8 15 35 60
9 35 35 60
10 15 35 80

Average daily demand = 1/10 (35+35+15+35+35+35+15+15+35+15)

= 270/10 = 27 Cakes
Example 2

• A company manufactures around 200 mopeds depending upon the

availability of raw materials and other conditions the daily production
has been wearing from 196 mopeds to 204 mopeds whose probability
distribution is as given below
Production/Day 196 197 198 199 200 201 202 203 204

Probability 0.05 0.09 0.12 0.14 0.20 0.15 0.11 0.08 0.06

• the finished mopeds are transported in a specially designed three

storied lorry that can accommodate only 200 mopeds using the
following 15 random numbers 82,89, 78,24, 53,61, 18,45,4,23,50,77,
27,54,10, simulate the mopeds waiting in the factory?
a) What will be the average number of mopeds waiting in the factory? b)
What will be the number of empty space in the lorry
Solution a) Using production per day distribution
the daily production distribution is shown in table
Production/Day Probability Cumulative Random Number Interval
Probability
196 0.05 0.05 00-04
197 0.09 0.14 05-13
198 0.12 0.26 14-25
199 0.14 0.40 26-39
200 0.20 0.60 40-59
201 0.15 0.75 60-74
202 0.11 0.86 75-85
203 0.08 0.94 86-93
204 0.06 1.00 94-99
Based on the 15 random numbers given, simulation experiment of the
production per day is shown in Table
Days Random RN Prod/ Prod/ per No. of mopeds Empty space in the Lorry
Number Intervals per day day as per Waiting
RN
1 82 00-04 196 202 2 0
2 89 05-13 197 203 5 0
3 78 14-25 198 202 7 0
4 24 26-39 199 198 5 0
5 53 40-59 200 200 5 0
6 61 60-74 201 201 6 0
7 18 75-85 202 198 4 0
8 45 86-93 203 200 4 0
9 04 94-99 204 196 0 0
10 23 198 0 2
11 50 200 0 0
12 77 202 2 0
13 27 199 1 0
14 54 200 1 0
15 10 197 0 2
• Average number of mopeds waiting in the factory =
= 1/15 (2+5+7+5+5+6+4+4+2+1+1) = 2.8

Average number of empty spaces in the lorry = 4/15 =0.27

Example for practice
• A trader deals in a perishable commodity. The daily demand is a
random variable. Records of Past 100 days show the following
Demand 1 2 3 4 5
No. of Days 10 20 30 30 10

• The trader buys the commodity at Rs. 10 per unit and sells at Rs. 15
per unit. Calculate the profits in 10 days by simulating the system. Use
following random numbers
12,75,14,72,20,82,74,08,01,69