Chapter-2- Forecasting

Faculty –N.K.Das
Unit-1
 Agenda

• What is forecasting?

• Understanding how forecast is essential

• Types of Forecasting.
– Qualitative

– Quantitative
 Introduction to Demand Forecasting

• Definition of Demand Forecasting

• Importance of Demand Forecasting

• Role in Business Decision Making

 Demand Forecasting
• Demand forecasting is the process of estimating future
customer demand for a product or service. It plays a crucial
role in various business decisions, from production
planning to inventory management.

• Key Points:
– Predicting Future Demand: Anticipating customer needs and
preferences helps businesses allocate resources effectively.
– Strategic Decision-Making: Accurate forecasts guide decisions
related to production, procurement, and marketing strategies.
– Business Growth: Effective demand forecasting supports
business growth by minimizing stock outs and excess inventory.
Examples Of Forecasting
Examples Of Forecasting
Examples Of Forecasting

Examples of
FMCGs
include milk, gum,
fruit and
vegetables, toilet
paper, soda, beer,
and over-the-
counter drugs like
aspirin.
Examples Of Forecasting
Examples Of Forecasting
Example of Forecasting
 Forecasting techniques can
depend on

•Time frame
– Indicates how far into the future is forecast
•Short- to mid-range forecast
– typically encompasses the immediate future
– daily up to two years
•Long-range forecast
• usually encompasses a period of time longer than
two years
 Forecasting techniques can
depend on

•Demand behavior
–Trend: a gradual, long-term up or down movement of
demand
–Random variations: movements in demand that do not
follow a
pattern
–Cycle: an up-and-down repetitive movement in demand
–Seasonal pattern: an up-and-down repetitive movement
in
demand occurring periodicall
 Elements of Good Forecast

• The forecast Should be timely.

– A certain amount of time is going to be needed to respond to a new
forecast. Capacity can’t be expanded overnight, and in order to increase or
reduce production to meet the forecast you’re going to need enough time
to reconfigure your equipment and processes. Accordingly, try to leave
enough time in your forecasting to cover any potentially needed changes.

• The forecast should be accurate.

– Sure, this sounds a little obvious, but any forecasting needs to be as
accurate and researched as possible. This will enable any user to plan for
possible error, and will provide a good basis for comparing alternative
forecasts.

• The forecast should be reliable.

Benefits of Demand Forecasting
• Demand forecasting provides several benefits to businesses across
different industries. It enables them to make informed decisions
that contribute to efficient operations and enhanced customer
satisfaction.
• Key Points:
– Inventory Management: Forecasting helps maintain optimal inventory
levels, reducing carrying costs and minimizing stock outs.
– Resource Allocation: Accurate predictions aid in allocating resources
like labor, raw materials, and production capacity effectively.
– Cost Efficiency: Matching supply to demand prevents overproduction
and waste, leading to cost savings.
– Market Responsiveness: Timely adjustments to production and
marketing strategies based on forecasts improve responsiveness to
market changes
 Strategic Importance
of Forecasting
• Human Resources – Hiring, training, laying off
workers
• Capacity – Capacity shortages can result in
undependable delivery, loss of customers,
loss of market share
• Supply-Chain Management – Good supplier
relations and price advance
 The Realities!

 Forecasts are seldom perfect

 Most techniques assume an underlying
stability in the system-"Most techniques assume an
underlying stability in the system" refers to a common assumption made in
various analytical and forecasting methods. This assumption implies that
the system being analyzed or forecasted will continue to behave in a
relatively consistent and predictable manner over a certain period of time.

 Product family and aggregated forecasts

are more accurate than individual product
forecasts
 Methods Of Forecasting
• Various methods are used to forecast demand,
each suited to different data availability,
accuracy requirements, and business contexts.
• Key Points:
– Qualitative Methods: Expert opinions, market
research, and Delphi method are used when
historical data is scarce or unreliable.
– Quantitative Methods: Time series analysis and
causal forecasting rely on historical data patterns
and external variables.
Forecasting Techniques
Unit-2
 Qualitative Method

Survey Consumer Survey

Method

Executive opinion
Qualitative
Method
Opinion Polls Sales force Opinion

Delphi Method
 Consumer Survey

• Consumer surveys ask customers of a business about

their experience as a consumer. Companies might
send consumer surveys to customers through mail-in
questionnaires or forms sent through email.

• After collecting information from consumer surveys,

employees can use the details they learn to help
inform their predictions about a company's future
based on the experience of their existing customers.
 Sales force Opinion

• Sales force polling involves speaking with sales staff

who work closely with customers and might have
thorough information about their satisfaction and
experiences with the company.
• One advantage of sales force polling is that it uses
information from employees who are most
frequently involved in the actual business operations,
which can ensure that the details are correct and
relevant.
 Executive opinion

• This approach relies on judgments from experts in

sales, finance, purchasing, administration or
production teams.
• Forecasting by executive opinion can ensure that a
team completes a forecast quickly and considers
multiple perspectives from different departments to
best inform their forecast.
• Some companies might use executive opinion
forecasting along with a quantitative method.
 Delphi method

• The Delphi method involves questioning a panel of

experts individually to collect their opinions.
Interviewing or gathering information from the
experts one at a time rather than in a group can
help to prevent bias and ensure that any consensus
about business predictions stems from the expert
opinions on their own.
 Delphi method

• Other employees then analyze the experts'

responses and return them with additional
questions until settling on a prediction that makes
sense for the company.
 Quantitative Methods

Forecast based on time series data

• Naïve Methods

• Moving average

• Weighted moving average

• Exponential Smoothing
 Naive Approach

 Assumes demand in next period is the

same as demand in most recent period
 e.g., If May sales were 48, then June sales
will be 48
 Sometimes cost effective and efficient
 Moving
Average

Jan Jan

Feb Feb Feb

Mar Mar Mar

Apr Apr Apr Apr

May May May May

June June June June

July July

Naïve Forecasting 3-month Moving Average

Unit-3
 Moving Average Method
 MA is a series of arithmetic means
 Used if little or no trend
 Used often for smoothing
 Provides overall impression of data over
time

∑ demand in previous n periods

Moving average = n
 Example-1
• Compute a three period moving average
forecast given demand for shopping carts for
the last five periods
Period Demand
1 42
2 40
3 43
4 40 For 3 most recent demands
5 41
 Example-1
Period Demand
1 42
2 40
3 43
4 40
For 3 most recent demands
5 41

F6= ( 43+40+41)/3

Ans: 41.33
 Moving Average Example
Actual 3-Month
Month Shed Sales Moving Average

January 10
February 12
March 13
April 16 (10 + 12 + 13)/3 = 11 2/3
May 19 (12 + 13 + 16)/3 = 13 2/3
June 23 (13 + 16 + 19)/3 = 16
July 26 (16 + 19 + 23)/3 = 19 1/3

Find Forecasting for the month of

1) April
2) May
3) June
4) July
 Weighted Moving Average

 Used when trend is present

 Older data usually less important
 Weights based on experience and
intuition
∑ (weight for period n)
x (demand in period n)
Weighted
moving average = ∑ weights
 Example-2
• a. Compute a weighted Period Demand
average forecast using a
weight of 0.40 for the 1 42
most recent period,for 2 40
the next recent
period,0.30 for the next 3 43
most recent,.20 and 0,1 4 40
for the next
5 41
• B. If the actual demand
for the period 6 is 39,
Forecast demand for
period 7 using the same Compute
weight as in part a. 1) F6
2) F7
 Example-2
• a. F6= 0.10*40+0.20*43+0.30*40+0.40*41=
41.0

• b. F7= 0.10*43+.20 *40+0.30*41+).40 *39=

40.2
 Quiz-1
• A qualitative forecast
a. predicts the quality of a new product.
b. predicts the direction, but not the magnitude, of
change in a variable.
c. is a forecast that is classified on a numerical scale
from 1 (poor quality) to 10 (perfect quality).
d. is a forecast that is based on econometric methods.
 Quiz-1
• A qualitative forecast
a. predicts the quality of a new product.
b. predicts the direction, but not the magnitude, of
change in a variable.
c. is a forecast that is classified on a numerical scale
from 1 (poor quality) to 10 (perfect quality).
d. is a forecast that is based on econometric methods.
 Quiz-2
• Forecasts are referred to as naive if they
a. are based only on past values of the
variable.
b. are short-term forecasts.
c. are long-term forecasts.
d. generally result in incorrect forecasts.
 Quiz-2
• Forecasts are referred to as naive if they
a. are based only on past values of the
variable.
b. are short-term forecasts.
c. are long-term forecasts.
d. generally result in incorrect forecasts.
 Quiz-3
• Which of the following is not a qualitative
forecasting technique?
a. Surveys of consumer expenditure plans
b. Perspectives of foreign advisory councils
c. Consumer intention polling
d. Time-series analysis
 Quiz-3
• Which of the following is not a qualitative
forecasting technique?
a. Surveys of consumer expenditure plans
b. Perspectives of foreign advisory councils
c. Consumer intention polling
d. Time-series analysis
 Weights Applied Period

Weighted Moving Average

3
2
Last month
Two months ago
1 Three months ago
6 Sum of weights

Actual 3-Month Weighted

Month Shed Sales Moving Average

January 10
February 12
March 13
April 16 [(3 x 13) + (2 x 12) + (10)]/6 = 121/6
May 19 [(3 x 16) + (2 x 13) + (12)]/6 = 141/3
June 23 [(3 x 19) + (2 x 16) + (13)]/6 = 17
July 26 [(3 x 23) + (2 x 19) + (16)]/6 = 201/2
 Exponential Smoothing
 Form of weighted moving average
 Weights decline exponentially
 Most recent data weighted most
 Requires smoothing constant ()
 Ranges from 0 to 1
 Subjectively chosen
 Involves little record keeping of past data
 Exponential Smoothing

New forecast = last period’s forecast

+  (last period’s actual demand
– last period’s forecast)

Ft = Ft – 1 + (At – 1 - Ft – 1)
where Ft = new forecast
Ft – 1 = previous forecast
 = smoothing (or weighting)
constant (0    1)
 Smoothing Constant
• The smoothing constant, often denoted as
alpha (α), is a key parameter in exponential
smoothing forecasting methods.
• It determines the weight given to the most
recent observation when making predictions.
The significance of the smoothing constant
lies in its impact on how the forecasted values
are calculated and how the model responds to
changes in the data.
 Effect of
Smoothing Constants

Weight Assigned to
Most 2nd Most 3rd Most 4th Most 5th Most
Recent Recent Recent Recent Recent
Smoothing Period Period Period Period Period
Constant () (1 - ) (1 - )2 (1 - )3 (1 - )4

 = .1 .1 .09 .081 .073 .066

 = .5 .5 .25 .125 .063 .031

Exponential Smoothing Example

Previous forecast = 142 Ford Ecosport

Actual demand = 153
Smoothing constant  = .20
Exponential Smoothing Example

Previous forecast = 142

Actual demand = 153
Smoothing constant  = .20

New forecast = 142 + .2(153 – 142)

Exponential Smoothing Example

Previous forcast = 142 Ford Ecosport

Actual demand = 153
Smoothing constant  = .20

New forecast = 142 + .2(153 – 142)

= 142 + 2.2
= 144.2 ≈ 144 cars
Unit-4
 Forecasting Accuracy
• Accuracy based on historical error
performance of a forecast

• Three commonly used measures for

summarizing historical errors .
– Mean absolute deviation. (MAD)
– Mean squared error (MSE)
– Mean absolute percent error (MAPE)
 Common Measures of Error

Mean Absolute Deviation (MAD)

∑ |actual - forecast|
MAD =
n

The average absolute forecast error

 Common Measures of Error

Mean Squared Error (MSE)

∑ (actual-forecast)2
MSE =
n

The average of squared forecast errors

 Common Measures of Error

Mean Absolute Percent Error (MAPE)

n
100 ∑ |actuali - forecasti|/actuali
MAPE = i=1
n

The average absolute percent error

Concept of forecasting error
• From a computational standpoint, the
difference between these measure is that,

• MAD weights all error evenly

• MSE weights according to square value
• MAPE weights according relative error
 Concept of forecasting
error
• One use of these measures is to compare the
accuracy of alternative forecasting methods,

• For instance a manager could compare the

result of exponential smoothing with values
alpha of 0.1,0.2 and 0.3 to determine one that
yields the lowest MAD,MSE and MAPE for a
given set of data.
Concept of forecasting error
• The operations manager must settle on the
relative importance of historical performance
versus responsiveness whether to use
MAD,MSE or MAPE.
• MAD is the easiest to compute.
• MSE Squares error
• MAPE should be used when there is a need to
put errors in perspective.to put large errors in
prospective MAPE would be used.
Concept of forecasting error
• For Example
– An error of 10 in a forecast of 15 is huge.
Conversely an error of 10 of 10000 is significant .
Hence to put large errors in perspective ,MAPE
will be used.
 Choosing a forecasting
technique
• No single technique works best in every situation.
• Two most important factors are cost and
accuracy.
• Higher the accuracy, higher the cost.
• The Delphi method and executive opinion
methods are often used for long range planning.
• Moving average and exponential smoothing are
essentially short range techniques.
Computers in forecasting
• Computers play an important role in preparing
forecasts based on quantitative data.

• The excel templates and spreadsheet

approach manager revise forecast quickly.
 Example
• Compute MAD,MSE and MAPE for the
following data.
Period Actual(A) Forecast (F)
1 217 215
2 213 216
3 216 215
4 210 214
5 213 211
6 219 214
7 216 217
8 212 216
 Solutions
Period Actual Forecast Error IErrorI Error2 Error/Actual
*100
1 217 215 2 2 4 .92
2 213 216 -3 3 9 1.41
3 216 215 1 1 1 .46
4 210 214 -4 4 16 1.90
5 213 211 2 2 4 .94
6 219 214 5 5 25 2.28
7 216 217 -1 1 1 0.46
8 212 216 -4 4 16 1.89
22 76 10.26%

MAD= ∑ I e I MSE= ∑ I e^2 I MAPE= ∑ I e I/Actual*100

n n n 1.28%
2.75 9.5
 Evaluating
Forecasts
Week Forecast (F1) Demand (D1)
1 92 88
2 87 88
3 95 97
4 90 83
5 88 91
6 93 93

Week Forecast (F2) Demand (D2)

1 96 91
2 89 89
3 92 90
4 93 90
5 90 86
6 85 89
 Evaluating
Forecasts
Week Forecast (F1) Demand (D1) E1 E1^2 E1/D1
1 92 88 4 16 0.045
2 87 88 1 1 0.011
3 95 97 2 4 0.021
4 90 83 7 49 0.084
5 88 91 3 9 0.033
6 93 93 0 0 0.000

Week Forecast (F2) Demand (D2) E2 E2^2 E2/D2

1 96 91 5 25 0.055
2 89 89 0 0 0.000
3 92 90 2 4 0.022
4 93 90 3 9 0.033
5 90 86 4 16 0.047
6 85 89 4 16 0.045
 Evaluating Forecasts
• MAD1 = 17/6 = 2.83
• MAD2 = 18/6 = 3

• MSE1 = 79/6 = 13.17

• MSE2 = 70/6 = 11.67

• MAPE1 = 0.0325
• MAPE2 = 0.0336
 Example
Given the following data,
Period No of Prepare a forecast using each of these approach
complain 1. The appropriate naive approach
1 60 2. A three period moving average
2 65 3. A weighted average using weights 0.5 (most
recent) 0.30 and 0.20.
3 55
4. exponential smoothing with a smoothing
4 58 constant 0.40
5 64 5. Find MAD ,MSE and MAPE
 Solution
1. The values are stable. Therefore ,the most
recent value of the series becomes the next
forecast.
The next forecast-64
 Solution
2. Since we have to find out three period moving
average ,
MA3 = 55+58+64
= 59
3
 Solution
3. Forecast (F) = 0.5 x 64 + 0.3 x 58 + 0.2 x 55
= 60.4
 Solution
Period No of complain Forecast Calculations
1 60
2 65 60 The previous value of the series is
used as starting forecast
3 55 62 60 + 0.4 ( 65 – 60) = 62
4 58 59.2 62 + 0.4 (55- 62) = 59.2
5 64 58.72 59.2 + 0.4 (58- 59.2) = 58.72
6 60.83 58. 72+ 0.4 (64- 58.72) = 60.83

Ans: 60.83
Solution
 Comparison of Forecast Error
Rounded Absolute Rounded Absolute
Actual Forecast Deviation Forecast Deviation
Tonnage with for with for
Quarter Unloaded  = .10  = .10  = .50  = .50
1 180 175 5 175 5
2 168 176 8 178 10
3 159 175 16 173 14
4 175 173 2 166 9
5 190 173 17 170 20
6 205 175 30 180 25
7 180 178 2 193 13
8 182 178 4 186 4
84 100
 Comparison of Forecast Error
∑ |deviations|
Rounded Absolute Rounded Absolute
MADActual
= Forecast Deviation Forecast Deviation
Tonage n
with for with for
Quarter Unloaded  = .10  = .10  = .50  = .50
1
For  =180
.10 175 5 175 5
2 168 = 84/8176
= 10.50 8 178 10
3 159 175 16 173 14
4 For  =175
.50 173 2 166 9
5 190 173 17 170 20
6 205 = 100/8
175= 12.50 30 180 25
7 180 178 2 193 13
8 182 178 4 186 4
84 100
 Comparison of Forecast Error
∑ (forecast errors)2
Rounded Absolute Rounded Absolute
MSE = Actual Forecast Deviation Forecast Deviation
Tonage
n
with for with for
Quarter Unloaded  = .10  = .10  = .50  = .50
1
For  =180
.10 175 5 175 5
2 = 1,558/8176
168 = 194.75 8 178 10
3 159 175 16 173 14
4 For  =175
.50 173 2 166 9
5 190 173 17 170 20
6 = 1,612/8175
205 = 201.50 30 180 25
7 180 178 2 193 13
8 182 178 4 186 4
84 100
MAD 10.50 12.50
 Comparison
n
of Forecast Error
100 ∑ |deviationi|/actuali
MAPE = Actual i = Rounded
1 Absolute Rounded Absolute
Forecast Deviation Forecast Deviation
Tonage with n for with for
Quarter Unloaded  = .10  = .10  = .50  = .50
1
For 180
= .10 175 5 175 5
2 168 = 45.62/8
176 = 5.70%
8 178 10
3 159 175 16 173 14
4 For 175
= .50 173 2 166 9
5 190 173 17 170 20
6 205 = 54.8/8
175 = 6.85%30 180 25
7 180 178 2 193 13
8 182 178 4 186 4
84 100
MAD 10.50 12.50
MSE 194.75 201.50
 Comparison of Forecast Error
Rounded Absolute Rounded Absolute
Actual Forecast Deviation Forecast Deviation
Tonnage with for with for
Quarter Unloaded  = .10  = .10  = .50  = .50
1 180 175 5 175 5
2 168 176 8 178 10
3 159 175 16 173 14
4 175 173 2 166 9
5 190 173 17 170 20
6 205 175 30 180 25
7 180 178 2 193 13
8 182 178 4 186 4
84 100
MAD 10.50 12.50
MSE 194.75 201.50
MAPE 5.70% 6.85%
 Case Study-4
• AI to replace 5% full-time tech roles annually
in five years: Experts

Read more at:

https://economictimes.indiatimes.com/tech/t
echnology/ai-to-replace-5-full-time-tech-roles-
annually-in-five-years-
experts/articleshow/102811992.cms?utm_so
urce=contentofinterest&utm_medium=text&u
tm_campaign=cppst
 Case Study-5
• india's semi conductor industry: from chip
shortages to global hub ambition.

• India semiconductors has emerge as key

players In the global market.

• Source : the economic times dated 18/08/23

Thank You
Reference Book(s)
1.Jacobs, F. R., & Chase, R. B. (2017).
Operations and Supply Chain
Management (15th ed.), McGraw Hill
Education.
2. Operations Management- William J
Stevenson-10th edition