NARSEE MONJEE INSTITUTE OF MANAGEMENT STUDIES (NMIMS)

GLOBAL ACCESS SCHOOL FOR CONTINUING EDUCATION

(NGA-SCE)

INTERNAL ASSIGNMENT

COURSE: DECISION SCIENCE

APPLICABLE FOR APRIL 2022 EXAMINATION
NMIMS GLOBAL ACCESS SCHOOL FOR CONTINUING EDUCATION (NGA-
SCE)
COURSE: DECISION SCIENCE
INTERNAL ASSIGNMENT APPLICABLE FOR APRIL 2022 EXAMINATION

QUES 1.) The table mentioned below shows the “Gross Production of Energy by Two
Sources in India from 2010-11 to 2015-16”.
Adopt Exponential Smoothing Method. Consider the Alpha (α) values 0.2, 0.5, 0.7 and
find out the one that is comparatively good for the prediction.
Forecast the value for year 2016-17.
Year Coal- (Million Tones) Lignite- (Million Tones)
2010-11 532.7 37.73
2011-12 539.95 42.33
2012-13 556.4 46.45
2013-14 565.77 44.27
2014-15 609.18 48.27
2015-16 639.23 43.84
Source: Open Government Data (OGD) Platform India

ANSW 1.) EXPONENTIAL SMOOTHING METHOD

DEFINITION
Exponential smoothing technique is first defined in the statistical literature without the
reference of previous work by Robert Goodell Brown in the year 1956 and then it was
expanded by Charles C. Holt in 1957.
It is defined as follows
“Exponential smoothing is a broadly accurate principle for smoothing time series data
using the exponential window function. The controlling input of the exponential
smoothing calculation is defined as the smoothing factor or the smoothing constant.”
MEANING
In simple words, exponential smoothing method is understood as Exponential smoothing
is a long sequence checking method for univariate statistics that may loosen up to assist
an orderly example or infrequent element. Notable smoothing is a duration series
assessing method for univariate records. Time-series strategies like the (field-Jenkins
A.R.I.M.A.) collecting of systems domesticate a version that predicts a weighted direct
measure of past due beyond insights or slacks.
EXPONENTIAL SMOOTHING FORMULA
The simplest form of an exponential smoothing formula is given by:

Exponential Smoothing (st) = αxt+(1 – α)st-1= st-1+ α(xt – st-1)

Here,
st = smoothed statistic, it is the simple weighted average of current observation xt
st-1 = previous smoothed statistic
α = smoothing factor of data; 0 < α < 1
t = time period
If the value of the smoothing factor is larger, then the level of smoothing will reduce.
Value of α close to 1 has less of a smoothing effect and give greater weight to recent changes in
the data,
while the value of α closer to zero has a greater smoothing effect and are less responsive to
recent changes.
As per the above given data
Alpha value 0.7 is a high value for alpha, which tracks the data more closely by giving more
weight to recent data results in the smallest MSE. This way it is most preferable.
The forecast for year 2016-2017 is 447.46 and 30.69 respectively.
 QUES 2.) Consider the following Decision alternative for the Raman Pahwa, he wants to
invest in stocks, and thought about two situations about tomorrow’s market condition.
The figures (in INR) in the following table exhibit profit per unit of stock-investment.

Payoff Table:

Favorable Market Unfavorable Market

Lakshmi Pvt. Ltd. 55 26

Mehta Group of Industries 43 38
Surya 29 43
LT energy 15 51

1. Draw the decision tree

2. If we assign the following probabilities to the states of nature,
then determine the EMV decision. P(s1) = 0.4 P(s2) =0 .1 P(s3) = 0.3 P(s4) = 0.2

ANSW 2.) As per the above given data and the problem mentioned above, the solution to
the below mentioned parts is given as follows-

1. DECISION TREE
A decision tree is a flowchart-like structure in which each internal node represents a "test" on an
attribute
(e.g. whether a coin flip comes up heads or tails),
each branch represents the outcome of the test, and each leaf node represents a class label
(decision taken after computing all attributes).
The paths from root to leaf represent classification rules.
In decision analysis, a decision tree and the closely related influence diagram are used as a visual
and analytical decision support tool, where the expected values (or expected utility) of competing
alternatives are calculated.

A decision tree consists of three types of nodes-

1. Decision nodes – typically represented by squares

2. Chance nodes – typically represented by circles
 3. End nodes – typically represented by triangles

As per the above mentioned data, the decision table is drawn as follows-
2. If we assign the following probabilities to the states of nature, then determination of
the EMV decision is done as follows-
EMV DECISION= (4*2) + (4*3)
= (8+12)
= 20
Where the term EMV decision is defined as follows-
Expected monetary value is a statistical concept that calculates the normal consequence
when the future contains scenarios that may or may not transpire. An EMV analysis is
usually recorded using a decision tree to stand for making decisions when facing multiple
risks in events and their possible consequences on scenarios. The expected monetary
value is a significant concept in project risk management which is for all types of
schemes to create a quantitative risk analysis. As a risk management tool, the Expected
Monetary Value can be used in projects to quantify and compare risks.
QUES 3
3.a. The proportion of eligible voters in the next corporation election (in tumkur) who
will vote for the incumbent is assumed to be 55%. What is the probability that in a
random sample of 500 voters less than 49% say they will vote for the incumbent? Write
your conclusion.
Answ 3.a. Probability sampling is generally defined as a sampling technique in which
the researcher chooses samples from a larger population using a method based on
the theory of probability. For a participant to be considered as a probability sample,
he/she must be selected using a random selection.
p˄ is normally distributed with a mean of µp˄ = p and a standard deviation
πp˄ = √ p (1-p)
n
Given p = 0.55, n = 500

P(p˄ < 0.49) = P (Z < 0.49-0.55)

√0.55(1-0.55)
500
≈ P( Z < -2.6968 ) ≈ 0.0035
CONCLUSION- From the above calculation it can be understood that the probability
that the voter will vote for the incumbent in percentage of less than 49% is 0.0035.

3.b. The top-selling Amar tire is rated 70,000 KMs, which means nothing. In fact, the
distance the tires can run until they wear out is a normally distributed random variable
with a mean of 82,000 KMs and a standard deviation of 6,400 KMs.
A.What is the probability that a tire wears out before 70,000 KMs?
B.What is the probability that a tire lasts more than 100,000 KMs?
Note: You may use Z-table for this.

Answ 3b.
Tire rated of Amar = 70,000 kms
Expected kms for which tyres can be run = 82,000 kms
Standard deviation = 6,400 kms
A
70,000- 82,000 = - 12,000 – 12,000 / 6400
= -1.875

CONCLUSION- The probability that tire wears out before 70,000 kms is 1.875.

B
1,00,000 – 82,000 = 18,000 – 18000 / 6400
= 2.8125

CONCLUSION- The probability that tires lasts more than 1,00,000 kms is 2.8125.