Chapter 7
Demand Forecasting
Text Book:
William J. Stevenson, Operations
Management, 8th ed., McGraw-Hill. Garrison
What is Forecasting?
Process of predicting a
Sales will
future event be $200
Underlying basis of Million!
all business decisions
Production
Material Requirement
Personnel
Facilities
Budgeting
Steps in Forecasting Process
Determine the purpose
Establish a time horizon
Select a forecasting technique
Gather and analyze the appropriate data
Prepare the forecast
Monitor the forecast
Types of Forecasts by Time
Horizon
Short-range forecast
Usually less than 3 months
Job scheduling, worker assignments
Medium-range forecast
3 months to 3 years
Sales & production planning, budgeting
Long-range forecast
3+ years
New product planning, facility location
Forecasting Approaches
Qualitative Methods Quantitative Methods
Used when situation is Used when situation is
vague & little data exist ‘stable’ & historical data
New products exist
New technology Existing products
Involves intuition, Current technology
experience Involves mathematical
e.g., First arrival of android techniques
phone. e.g., Forecasting demand of
Rod of a steel plant
Qualitative Methods
Sales force composite
Jury of executive opinion
Delphi method
Consumer Market Survey
Sales Force Composite (or grass
roots forecasting)
Person closest to customer ends
Sale
knows best
s
Combines each levels
Sales representatives know
customers’ wants
Retailer © 1995
Corel Corp.
Distributor
Manufacturer
Jury of Executive Opinion (or
panel consensus)
Involves people from various positions in the
organization
Group estimates demand by working together
Relatively quick
Free exchange of ideas
Lower employee levels
may get intimidated
by higher management.
© 1995 Corel Corp.
Delphi Method
Iterative group process. Conceals
identity of participants
Moderator makes a questionnaire.
Response are summed and new set of
questions are provided
Step by step procedure
1.Choose the experts to participate.
2.Through a question set obtain forecasts from
the participants.
3.Summarize the results and redistribute them to
the participants along with new set of question.
4.Summarize again.
5.Repeat step 3 & 4 until consensus is reached
Consumer Market Survey (or
Market Research)
How many hours
Ask customers about will you use the
purchasing plans Internet next week?
What consumers
say, and what they
actually do are often
different
Sometimes difficult to
answer
© 1995 Corel
Corp.
Quantitative Approaches
Naïve approach
Moving averages
Exponential smoothing
Trend projection
Linear regression
Naive Approach
Assumes demand in next period
is similar as demand in most
recent period without adjusting
them considering any factor.
e.g., If May sales were 48, then
June sales will be …48
Sometimes cost effective &
efficient
© 1995 Corel Corp.
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
Equation
MA Demand in Previous n Periods
n
Moving Average Example
You’re manager of a museum store that sells
historical replicas. You want to forecast sales
2000 for 2003 using a 3-period moving average.
1998 4
1999 6
2000 5
2001 3
2002 7
Moving Average Solution
Time Response Moving Moving
Yi Total Average
(n=3) (n=3)
1998 4 NA NA
1999 6 NA NA
2000 5 NA NA
2001 3 4+6+5=15 15/3 = 5
2002 7
2003 NA
Moving Average Solution
Time Response Moving Moving
Yi Total Average
(n=3) (n=3)
1998 4 NA NA
1999 6 NA NA
2000 5 NA NA
2001 3 4+6+5=15 15/3=5.0
2002 7 6+5+3=14 14/3=4.7
2003 NA 5+3+7=15 15/3=5.0
Moving Average Solution
A moving average forecast tends to smooth and lag
changes in the data
Moving Average Solution
The more periods in a moving average, the greater the
forecast will lag changes in the data
Weighted Moving Average Method
Used when trend is present
Older data usually less important
Weights based on intuition
Often lay between 0 & 1, & sum to 1.0
Equation
Weighted Moving Average Method
What is the sales forecast for Month 5?
Ans: =0.4*95+ .3*105+ .2*90+ .1*100
= 97.5 units
Exponential Smoothing Method
Form of weighted moving average
Weights decline exponentially
Most recent data weighted most
Requires smoothing constant ()
Ranges from 0 to 1
Involves little record keeping of past data
Exponential Smoothing Equations
Ft = Ft-1 + (At-1 - Ft-1)
Ft = Forecast value
At = Actual value
= Smoothing constant
At-1 - Ft-1= Forecast error.
Exponential Smoothing Example
During the past 8 quarters, the Port of Mongla has unloaded large quantities of
grain. ( = .10). The first quarter forecast was 175..
Quarter Actual
1 180
2 168
Find the forecast
3 159
for the 9th quarter.
4 175
5 190
6 205
7 180
8 182
9 ?
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, F t
Quarter Actual
( α = .10)
1 180 175.00 (Given)
2 168 175.00 +
3 159
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, F t
Quarter Actual
Actua
( α = .10)
1 180 175.00 (Given)
2 168 175.00 + .10(
3 159
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, Ft
Quarter Actual
(α = .10)
1 180 175.00 (Given)
2 168 175.00 + .10(180 -
3 159
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, Ft
Quarter Actual
(α = .10)
1 180 175.00 (Given)
2 168 175.00 + .10(180 - 175.00)
3 159
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, Ft
Quarter Actual
(α= .10)
1 180 175.00 (Given)
2 168 175.00 + .10(180 - 175.00) = 175.50
3 159
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, F t
Quarter Actual
( α = .10)
1 180 175.00 (Given)
2 168 175.00 + .10(180 - 175.00) = 175.50
3 159 175.50 + .10(168 - 175.50) = 174.75
4 175
5 190
6 205
Exponential Smoothing Solution
Ft = Ft-1 + (At-1 - Ft-1)
Forecast, F t
Time Actual
(α = .10)
4 175 174.75 + .10(159 - 174.75) = 173.18
5 190 173.18 + .10(175 - 173.18) = 173.36
6 205 173.36 + .10(190 - 173.36) = 175.02
7 180 175.02 + .10(205 - 175.02) = 178.02
8 182 178.02 + .10(180 - 178.02) = 178.22
9 ? 178.22 + .10(182 - 178.22) = 178.58
Effect of α in forecasting
Linear Regression
Least Squares Method
Actual
observation Deviation
Values of Dependent Variable
Deviation Deviation
Deviation
Deviation Point on
regression
Deviation line
Deviation
Yˆ a bx
Time
Linear Trend Projection
Used for forecasting linear trend line
Assumes relationship between response
variable, Y, and time, X, is a linear function
Yi a bX i
Estimated by least squares method
Minimizes sum of squared errors
Least Squares Equations
Equation:
Ŷi a bx i
n
xi yi nx y
Slope: b i 1
n
2 2
x n(x )
i
i 1
Y-Intercept:
a y bx
Using a Trend Line
The demand for
electrical power at N.
Year Demand (MW)
Y. Edison over the
1997 74 years 1997-2003 is
1998 79 given at the left. Find
1999 80 the overall trend. Also
2000 90 find the demand at
2004 and 2005.
2001 105
2002 142
2003 122
Finding a Trend Line
Year Time Power x2 xy
Period Demand
1997 1 74 1 74
1998 2 79 4 158
1999 3 80 9 240
2000 4 90 16 360
2001 5 105 25 525
2002 6 142 36 852
2003 7 122 49 854
x=28 y=692 x2=140 xy=3,063
The Trend Line Equation
Σx 28 Σy 692
x 4 y 98.86
n 7 n 7
Σxy - n x y 3,063 (7)(4)(98.86) 295
b 2 2
2
10.54
Σx nx 140 (7)(4) 28
a y - bx 98.86 - 10.54(4) 56.70
Overall Trend, Y 56.70 10.54X
Demand in 2004 56.70 10.54(8) 141.02 megawatts
Demand in 2005 56.70 10.54(9) 151.56 megawatts
Practice Problem
Ans: Y= 441.6+ 359.6X
Non-Linear Trend
Polynomial Modelling
The general form of a quadratic polynomial regression
Y = a0 + a1t + a2t2
Where,
Y = Demand/ Forecasted Value
t = time period
a0, a1, a2 = Model parameters need to determine
Polynomial Modelling
Year Demand
(MW)
1997 74 The demand for electrical
1998 79 power at N. Y. Edison over
the years 1997-2003 is
1999 80
given at the left. Find the
2000 90 overall trend. Also find the
2001 105 demand at 2004 and 2005.
2002 142
2003 122
Polynomial Modelling
Calculation of the required values:
Polynomial Modelling
Polynomial Modelling
System of normal equations:
692 = 7a0 + 28a1 + 140a2
3063 = 28a0 + 140a1 + 784a2
16265 = 140a0 + 784a1 + 4676a2
Solving the equations yields:
a0 = 66
a1 = 4.345
a2 = 0.7738
The polynomial equation will be:
Y = 66 + 4.345t + 0.7738t2
