2.

1 FORECASTING DEMAND

Question 1: What are the objectives and uses of forecasting?

Answer 1: Forecasts are estimates of the occurrence, timing or magnitude of uncertain future events.
Forecasts are essential for the smooth operations of business organizations. They provide information
that can assist managers in guiding future activities towards organizational goals.

Question 2: What is long range forecast? Also write its purpose.

Answer 2: Long range forecast has a time span of more than 3 years
1. To work out expected capital expenditure for future developments or to acquire new facilities,
2. To determine expected cash flow from sales,
3. To plan for future manpower requirements,
4. To plan for material requirement,
5. To plan for Research and Development. Here much importance is given to long range growth
factor.

Question 3: What is medium range forecast? Also write its purpose.

Answer 3: Medium range forecast has a time span between 1 – 2 years
1. To determine budgetary control over expenses,
2. To determine dividend policy,
3. To find and control maintenance expenses,
4. To determine schedule of operations,
5. To plan for capacity adjustments.

Question 4: What is short-term forecast? Also write its purpose.

Answer 4: Short-term forecast has a time span between a few weeks to six months
1. To estimate the inventory requirement,
2. To provide transport facilities for finished goods,
3. To decide workloads for men and machines,
4. To find the working capital needed,
5. To set-up of production run for the products,
6. To fix sales quota,
7. To find the required overtime to meet the delivery promises.

[CMA RTP D10]

Question 5: Write short note on factors affecting business forecast.
Answer: Forecasting means peeping into the futures. As future is unknown and is anybody’s guess
but the business leaders in the past have evolved certain systematic and scientific methods to know
the future by scientific analysis based on facts and possible consequences. Thus, this systematic
method of probing the future is called forecasting. In this way forecasting of sales refers to an act of
making prediction about future sales followed by a detailed analysis of facts related to future

Production Planning and Productivity Management 2.1.1

situations and forces which may affect the business as a whole. Foresight is not the whole of
management, but at least it is an essential part of management and accordingly, to foresee in this
context means both to assess the future and make provisions for it, that is forecasting is itself action
already. Forecasting as a kind of future picture wherein proximate events are outlined with some
distinctness, while remote events appear progressively less distinct and it entails the running of the
business as foresee and provide means to run the business over a definite period.
Various factors that influence the forecast are:
1. Environmental changes,
2. Changes in the preference of the user,
3. Number of competitive products,
4. Disposable income of the consumer.
In forecasting the production important factors to be considered are:
1. Demand from the marketing department,
2. Rate of labors absenteeism,
3. Availability of materials,
4. Available capacity of machines,
5. Maintenance schedules,
6. Delivery date schedules.

Question 6: Write down the steps in forecasting

Answer 6:
1. Determine the objective of forecast
2. Select the period over which the forecast will be made
3. Select the method you want to use for making the forecast
4. Gather information to be used in the forecast
5. Make the forecast

Question 7: What are the methods or techniques of sales forecasting?

Answer 7:
1. Survey of buyer’s inventions or the user’s expectation method
2. Collective opinion or sales force composite method
3. Group executive judgment or executive judgment method
4. Experts’ opinions
5. Market test method.
6. Trend projection method (a) Direct method (where ∑X = 0) (b) Indirect method
7. Moving average method

Question 8: What are the criteria of a good forecasting method?

Answer 8:
1. Accuracy
2. Simplicity
3. Economy

Forecasting Demand 2.1.2

4. Availability
5. Stability
6. Utility

PRACTICAL PROBLEMS
Three methods for describing trend are:
1. Moving average
2. Hand fitting, and
3. Least squares.

Question 1: MOVING AVERAGE: Shipments (in tons) of welded tube by an aluminum producer are
shown below:
Year 1 2 3 4 5 6 7 8 9 10 11
Tons 2 3 6 10 8 7 12 14 14 18 19

(a) Graph the data, and comment on the relationship.

(b) Compute a 3-year moving average, plot it as a dotted line, and use it to forecast shipments in year
12.
(c) Using a weight of 3 for the most recent data, 2 for the next, and 1 for the oldest, forecast
shipments in year 12
Answer:

3 year moving average

Year Tons 3-year 3-year
moving total moving average

1 2 - -
2 3 11 3.7
3 6 19 6.3
4 10 24 8.0
5 8 25 8.3
6 7 27 9.0

Production Planning and Productivity Management 2.1.3

 7 13 33 11.0
8 14 40 13.3
9 14 46 15.3
10 18 51 17.0
11 19 - -
(a) The data points appear relatively linear.
(b) See the above table for computations and figure for plot of the moving average. The moving
average forecast for year 12 would be that of the latest average, 17.0 tons.

∑(wt)X (1)(14)+ (2 )(18)+(3)19

(c) MAwt = ∑ WT
= = 17.8
1+2+3

Question 2: HAND FITTING OR HIGH/LOW METHOD: Use a hand fit line for the data given
belowand forecast tons for year 12

Year [X] 1 2 3 4 5 6 7 8 9 10 11
Tons [Y] 2 3 6 10 8 7 12 14 14 18 19

Answer 2: Select points some distance apart. A straight line connecting the values for years 3 and 8
might be a good free hand representation of the data. From this we can determine the slope and
intercept:
∆Y Y2−Y1 14 − 6
𝐒𝐥𝐨𝐩𝐞: b = = = 1.6 tons
∆X X2−X1 8−3

Intercept: a = 0.5 tons (Note: This is the estimated Y Value at X = 0 from graph.)
Equation: Yc = 0.5 + 1.6X (X = year, Y = tons)
For year 12: Yc = 0.5 + 1.6 (12) = 19.7 tons.

Question 3: LEAST SQUARES – INDIRECT METHOD: An investigation into the demand for color
TV sets in 5 towns has resulted in the following data:

Population of the town (in lakhs) [X] 5 7 8 11 14

Number of TV sets in demand (in thousands) [Y] 9 13 11 15 19

Fit a linear regression of Y on X and estimate the demand for CTV sets for two towns with a
population of 10 lakhs and 20 lakhs.

Forecasting Demand 2.1.4

Answer 3: Computation of trend values
Population Sales of CTV Squares of the Population ×
(in lakhs) (in thousands) Population Sales of CTV

X Y X2 XY
5 9 25 45
7 13 49 91
8 11 64 88
11 15 121 165
14 19 196 166
∑X = 45 ∑Y = 67 ∑X2 = 455 ∑XY = 655

Regression equation of Y on X:Y = a + bX

To find the values of a and b, the following two equations are to be solved
∑Y = na + b∑X ------ (i)
∑XY = a∑X + b∑X2 ------ (ii)
By substituting the values we get
67 = 5a + 45b ------ (iii)
655 = 45a +a455b ------ (iv)
Multiplying equation (iii) by 9 and we get (v),
603 = 45a + 405b ------ (v)
By deducting equation (v) from equation (iv); we get
52 = 50b
b = 52/50 = 1.04
By substituting the value of b in equation (iii), we get
67 = 5a + 45 × 1.04
Solving the above equation: a = 4.04
Now by substituting the values of a, b and X (10 lakhs) in regression equation of Y on X, we get,
Y = a + bX
Y = 4.04 + 1.04 (10) = 14.44 thousand CTV sets.
Similarly sales estimates for town having population of 20 lakhs is obtained by substituting the values
of X, a and b in regression equation
Y = 4.04 + 1.04 (20)= 24.84 thousands CTV sets.
Hence expected demand for CTV for two towns will be 14.44 thousand and 24.84 thousand CTV sets.

[CMA INTER D09, 6 Marks]

Question 4: LEAST SQUARES – DIRECT METHOD: From the following time series data of sale
project, the sales for the next three years

Production Planning and Productivity Management 2.1.5

 Year 2001 2002 2003 2004 2005 2006 2007
Sales (‘000 units) 80 90 92 83 94 99 92

Answer 4: Computation of Trend Values

Years Deviation Sales in Squares of Deviations
from 2004 (‘000 u) Deviation × sales

X Y X2 XY
2001 -3 80 9 -240
2002 -2 90 4 -180
2003 -1 92 1 -92
2004 0 83 0 0
2005 +1 94 1 +94
2006 +2 99 4 +198
2007 +3 92 9 +276
n=7 ∑X = 0 ∑Y = 630 ∑X2 = 28 ∑XY = +56

Regression equation of Y on X
𝑌 = 𝑎 + 𝑏𝑋
To find the values of a and b
∑y 630
a= = = 90
𝑛 7
∑𝑥𝑦 56
𝑏= 2
= = 2
∑𝑥 28
Hence regression equation comes to Y = 90 + 2X. with the help of this equation we can project the
trend values for the next three years, i.e. 2008, 2009 and 2010.
Y2008 = 90 + 2(4) = 90 + 8 = 98(000) units
Y2009 = 90 + 2(5) = 90 + 10 = 100(000) units
Y2010 = 90 + 2(6) = 90 + 12 = 102(000) units.

[CMA INTER J09, 4 Marks]

Question 5: The annual sales of TV sets by a dealer in Delhi are as under

Year 2004 2005 2006 2007 2008

Sales (‘000 units) 3 14 36 4 33
Fit a linear trend equation to the sales figure and estimate the sales for the year 2009.
Answer 5: Computation of Trend Values

Forecasting Demand 2.1.6

 Years Deviation Sales in Squares of Deviations
from 2004 (‘000 u) Deviation × sales

X Y X2 XY
2004 3 -2 4 -6
2005 14 -1 1 -14
2006 36 0 0 0
2007 4 1 1 4
2008 33 2 4 66
n=5 ∑X = 90 ∑Y = 0 ∑X2 = 10 ∑XY = +50

Regression equation of Y on X: Y = a + bX
Regression equation of Y on X
∑𝑦 90
𝑎= = = 18
𝑛 5
∑𝑥𝑦 905
𝑏= = =5
∑𝑥 2 10

Hence regression equation is a + bX or 18 + 5X.

With the help of this equation, the trend value for 2009 can be calculated as follows
𝒀𝟐𝟎𝟎𝟗 = 𝟏𝟖 = 𝟓(𝟑) = 𝟑𝟑, 𝟎𝟎𝟎 𝑼𝒏𝒊𝒕𝒔.

[CMA RTP J11]

Question 6: Estimate the number of scooters to be sold in a town with population of 12 lacs with help
of following data.
Population (in lacs) (X) 4 6 7 10 13
Number of scooters (Y) 5500 6600 5700 9000 10500
Answer 6:
Population Sale of Squares of Population
(in lacs) scooter population × sales
X Y X2 XY
4 5.5 16 22
6 6.6 36 39.6
7 5.7 49 39.9
10 9 100 90
13 10.5 169 136.5
ΣX = 40 ΣY = 37.3 ΣX2 = 370 ΣXY = 328
Regression equation of Y on X

Production Planning and Productivity Management 2.1.7

 Y = a + bX
ΣY = na + bΣX
ΣXY = aΣX + bΣX2
Thus,
[1] 37.3 5a + b × 40
[2] 328 a × 40 + b × 370

By solving the above equation, a = 2.724 & b = 0.592

By substituting value of a and b,
Y = 2.724 + 0.592 × 12 (lacs)
Y = 2.724 + 7.104
Y = 9.828 thousand scooters

[CMA INTER D08, 4 Marks]

Question 7: The following is the demand for Product A in 5 towns:

Population in (lacs) [X] 9 5 8 5 3

Demand [Y] 12 20 15 10 5
Estimate the demand for Product A for a town with a population of 10 lacs.
Answer 7: Computation of Trend Values
Population Demand
(in lacs)

X Y X2 XY
9 12 81 108
5 20 25 100
8 15 64 120
5 10 25 50
3 5 9 15
30 62 204 393
Regression equation of Y on X
Y = a + bX
ΣY = na + bΣX
ΣXY = aΣX + bΣX2
Thus,
[1] 62 5a + b × 30

Forecasting Demand 2.1.8

 [2] 393 a × 30 + b × 204

By solving the above equation, a = 7.15& b = 0.875

By substitutingthe values of a and b,
Y = 7.15 + 0.875 × 10
Y = 15.9 lakhs

[CMA INTER J10, 6 Marks]

Question 8: It is observed that there exists a relationship between expenditure on Advertising and
the Annual Sales. The details for last six years are as follows
Year Expenditure Annual Sales (₹)
on Advertising In crore

2004 1 18
2005 2 23
2006 4 32
2007 3 28
2008 10 38
2009 4 29
Estimate the Annual Sales when Expenditure on Advertising is ₹5 Crore.
Answer 8:
Years Expend. on Annual Sales
Advt.

X Y X2 XY
2004 1 18 1 18
2005 2 23 4 46
2006 4 32 16 128
2007 3 28 9 84
2008 10 38 100 380
2009 4 29 16 116
N=6 ∑X=24 ∑Y=168 ∑X2=146 ∑XY=772

24 ̅ 168
𝒀
̅=
𝑿 = 4 𝑎𝑛𝑑 = 28
6 6
Regression equation of Y on X: Y = a + bX
̅̅̅̅
∑𝑋𝑌 − 𝑛𝑿𝒀 772 − 6 × 4 × 28
𝑏 = = = 2
2
∑𝑋 − 𝑛𝑿̅ 2 146 − 6 × 42
𝑎=𝒀̅ − 𝑏𝑿 ̅ = 28 – 2 × 4 = 20

Production Planning and Productivity Management 2.1.9

 ̅ = 20 + 2𝐗
Thus, the model is 𝐘 ̅

The Annual sales when expenditure is 5 crore isY = 20 + 2×5 = 30 Crores.

[CMA INTER D09, 6Marks]

Question: From the following time series data of sales of refrigeratiors, project the sales for the
year 2010
Year 2002 2003 2004 2005 2006 2007 2008

Sales(thousand units) 90 100 102 93 104 109 102

Answer:
Years Sales Time Square of Product of time
Deviation time deviation deviation and Sales

Y X 𝑋2 XY
2002 90 -3 9 -270
2003 100 -2 4 -200
2004 102 -1 1 -102
2005 9 0 0 0
2006 104 1 1 104
2007 109 2 4 218
2008 102 3 + 306
n=7 ∑Y = 700 ∑X = 0 ∑𝑋 2 = 28 ∑XY = 56

Regression equation of Y on X
𝑌 = 𝑎 + 𝑏𝑋
For calculation the values of a and b
∑𝑌 700
𝑎 = = = 100
𝑛 7
∑𝑋𝑌 56
𝑏 = = 2
∑𝑋 2 28
Hence, regression equation is a + bX or 100+ 2X. With the help of this equation, the trend value for
2010 can be calculated as follows
𝑌2010 = 100 + 2(5) = 110 𝑢𝑛𝑖𝑡𝑠.

[CMA INTER J14, 6 Marks]

Question: The following data on the exports of an item by a company during the various years fit a
straight line, (for the time being, assume that a straight line gives a good fit). Give a forecast for the
years 2013 and 2014.
Year No.of items (‘000)

2004 13

Forecasting Demand 2.1.10

 2005 20
2006 20
2007 28
2008 30
2009 32
2010 33
2011 38
2012 43

Answer: Let ‘X’ represent year and ‘T’ represent export. In order to use the normal equations for the
least square line, we need ∑X, ∑Y, ∑XY and ∑𝑋 2 . To simplify the calculation arrange X in such a way
that ∑X = 0.
Therefore, we call the year 2008 as 0, 2007 as -1 and 2009 as +1 and likewise for the other years in the
data. The rearrangement is hown in the table as follows;
X Y 𝑿𝟐 XY

-4 13 16 -52
-3 20 9 -60
-2 20 4 -40
-1 28 1 -28
0 30 0 0
1 32 1 32
2 33 4 66
3 38 9 114
4 43 16 172
∑X = 0 ∑Y = 257 ∑𝑋 2 = 60 ∑XY = 204
The normal equations are:
∑Y = 𝑎0 N + 𝑎1 ∑X
∑XY = 𝑎0 X + 𝑎1 ∑𝑋 2
∑X = 0 and ∑Y = 𝑎0 N and ∑XY = 𝑎1 ∑𝑋 2
Therefore,
∑Y 257
𝑎0 = = = 28.56
𝑁 9
∑XY 204
𝑎1 = = = 3.4
∑𝑋 2 60

The equation of a straight line fitting the data is;

Y = 28.56 +3.4X
(a) Forecast for 2013, (i.e., X = 5): Y = 28.56 + 3.4(5) = 45.56
(b) Forecast for 2014, (ie., X =6): X 28.56 +3.4(6) = 48.96

Production Planning and Productivity Management 2.1.11