Professional Documents
Culture Documents
Management
Session 3
Forecasting
41
What is Forecasting?
Process of
predicting a future
event
Underlying basis of
??
all business
decisions
Production
Inventory
Personnel
Facilities
42
Medium-range forecast
3 months to 3 years
Sales and production planning, budgeting
Long-range forecast
3+ years
New product planning, facility location,
research and development
2008 Prentice Hall, Inc.
43
Distinguishing Differences
Medium/long range forecasts deal with
more comprehensive issues and support
management decisions regarding
planning and products, plants and
processes
Short-term forecasting usually employs
different methodologies than longer-term
forecasting
Short-term forecasts tend to be more
accurate than longer-term forecasts
2008 Prentice Hall, Inc.
44
Types of Forecasts
Economic forecasts
Address business cycle inflation rate,
money supply, housing starts, etc.
Technological forecasts
Predict rate of technological progress
Impacts development of new products
Demand forecasts
Predict sales of existing products and
services
2008 Prentice Hall, Inc.
45
46
Forecasting Approaches
Qualitative Methods
Used when situation is vague
and little data exist
New products
New technology
47
Forecasting Approaches
Quantitative Methods
Used when situation is stable and
historical data exist
Existing products
Current technology
48
Overview of Qualitative
Methods
Jury of executive opinion
Pool opinions of high-level experts,
sometimes augment by statistical
models
Delphi method
Panel of experts, queried iteratively
49
Overview of Qualitative
Methods
Sales force composite
Estimates from individual
salespersons are reviewed for
reasonableness, then aggregated
4 10
4 11
4 12
Delphi Method
Iterative group
process,
continues until
consensus is
reached
Staff
(Administering
3 types of
survey)
participants
Decision makers
Staff
Respondents
2008 Prentice Hall, Inc.
Decision Makers
(Evaluate
responses and
make decisions)
Respondents
(People who can
make valuable
judgments)
4 13
4 14
Overview of Quantitative
Approaches
1. Naive approach
2. Moving averages
3. Exponential
smoothing
Time-Series
Models
4. Trend projection
5. Linear regression
2008 Prentice Hall, Inc.
Associative
Model
4 15
4 16
Cyclical
Seasonal
Random
4 17
Components of Demand
Trend
component
Seasonal peaks
Actual
demand
Random
variation
|
1
|
2
|
3
Year
Average
demand over
four years
|
4
Figure 4.1
4 18
Trend Component
Persistent, overall upward or
downward pattern
Changes due to population,
technology, age, culture, etc.
Typically several years
duration
4 19
Seasonal Component
Regular pattern of up and
down fluctuations
Due to weather, customs, etc.
Occurs within a single year
Period
Length
Number of
Seasons
Week
Month
Month
Year
Year
Year
Day
Week
Day
Quarter
Month
Week
7
4-4.5
28-31
4
12
52
4 20
Cyclical Component
Repeating up and down movements
Affected by business cycle,
political, and economic factors
Multiple years duration
Often causal or
associative
relationships
0
2008 Prentice Hall, Inc.
10
15
20
4 21
Random Component
Erratic, unsystematic, residual
fluctuations
Due to random variation or
unforeseen events
Short duration and
nonrepeating
M
2008 Prentice Hall, Inc.
F
4 22
Naive Approach
Assumes demand in next
period is the same as
demand in most recent period
e.g., If January sales were 68, then
February sales will be 68
4 23
4 24
Actual
Shed Sales
10
12
13
16
19
23
26
3-Month
Moving Average
4 25
Shed Sales
Moving
Average
Forecast
Actual
Sales
|
J
|
F
|
M
|
A
|
M
|
J
|
J
|
A
|
S
|
O
|
N
|
D
4 26
4 27
Weights Applied
Period
3
Last month
Weighted Moving
Average
2
1
6
Month
Actual
Shed Sales
January
February
March
April
May
June
July
10
12
13
16
19
23
26
3-Month Weighted
Moving Average
4 29
30
Sales demand
25
20
Actual
sales
15
Moving
average
10
5
|
Figure 4.2
2008 Prentice Hall, Inc.
|
F
|
M
|
A
|
M
|
J
|
J
|
A
|
S
|
O
|
N
|
D
4 30
Exponential Smoothing
Form of weighted moving average
Weights decline exponentially
Most recent data weighted most
4 31
Exponential Smoothing
Ft = new forecast
Ft 1 = previous forecast
4 32
Exponential Smoothing
Example
Predicted demand = 142 Ford Mustangs
Actual demand = 153
Smoothing constant = .20
4 33
Exponential Smoothing
Example
Predicted demand = 142 Ford Mustangs
Actual demand = 153
Smoothing constant = .20
New forecast = 142 + .2(153 142)
4 34
Exponential Smoothing
Example
Predicted demand = 142 Ford Mustangs
Actual demand = 153
Smoothing constant = .20
New forecast = 142 + .2(153 142)
= 142 + 2.2
= 144.2 144 cars
4 35
Impact of Different
225
Demand
= .5
Actual
demand
200
175
150
|
1
|
2
|
3
|
4
|
5
|
6
= .1
|
7
|
8
|
9
Quarter
2008 Prentice Hall, Inc.
4 36
Impact of Different
Demand
225
200
Chose
when
underlying average
|
|
|
|
|
is stable
1
= .5
Actual
high values
of
demand
|
6
= .1
|
7
|
8
|
9
Quarter
2008 Prentice Hall, Inc.
4 37
Choosing
The objective is to obtain the most
accurate forecast no matter the
technique
We generally do this by selecting the
model that gives us the lowest forecast
error
Forecast error = Actual demand - Forecast value
= At - Ft
2008 Prentice Hall, Inc.
4 38
4 39
100|Actuali - Forecasti|/Actuali
MAPE =
i=1
4 40
Comparison of Forecast
Error
Quarter
Actual
Tonnage
Unloaded
Rounded
Forecast
with
= .10
Absolute
Deviation
for
= .10
1
2
3
4
5
6
7
8
180
168
159
175
190
205
180
182
175
175.5
174.75
173.18
173.36
175.02
178.02
178.22
5.00
7.50
15.75
1.82
16.64
29.98
1.98
3.78
82.45
Rounded
Forecast
with
= .50
175
177.50
172.75
165.88
170.44
180.22
192.61
186.30
Absolute
Deviation
for
= .50
5.00
9.50
13.75
9.12
19.56
24.78
12.61
4.30
98.62
4 41
Comparison of Forecast
Error
|deviations|
MADActual
=
Quarter
Tonnage
Unloaded
Rounded
Forecast
n
with
= .10
Absolute
Deviation
for
= .10
For
=
.10
1
180
175
5.00
2
168 = 82.45/8
175.5 = 10.31
7.50
3
4 For
5
6
7
8
159
174.75
175
= .50 173.18
190
173.36
205 = 98.62/8
175.02
180
178.02
182
178.22
15.75
1.82
16.64
12.33
29.98
1.98
3.78
82.45
Rounded
Forecast
with
= .50
175
177.50
172.75
165.88
170.44
180.22
192.61
186.30
Absolute
Deviation
for
= .50
5.00
9.50
13.75
9.12
19.56
24.78
12.61
4.30
98.62
4 42
Comparison of Forecast
Error
(forecast errors)
2
MSE = Actual
Quarter
Tonnage
Unloaded
Rounded
Forecast
n
with
= .10
Absolute
Deviation
for
= .10
For
=
.10
1
180
175
5.00
2
168
175.5 = 190.82
7.50
= 1,526.54/8
3
4 For
5
6
7
8
159
174.75
175
= .50 173.18
190
173.36
= 1,561.91/8
205
175.02
180
178.02
182
178.22
MAD
15.75
1.82
16.64
195.24
29.98
1.98
3.78
82.45
10.31
Rounded
Forecast
with
= .50
175
177.50
172.75
165.88
170.44
180.22
192.61
186.30
Absolute
Deviation
for
= .50
5.00
9.50
13.75
9.12
19.56
24.78
12.61
4.30
98.62
12.33
4 43
Comparison of Forecast
n
Error|/actual
100|deviation
i
i=1
MAPE =
Actual
Tonnage
Quarter Unloaded
1
2
3
4
5
6
7
8
Rounded
Absolute
Forecast n Deviation
with
for
= .10
= .10
For 180
= .10 175
5.00
168
175.5
= 44.75/8
= 7.50
5.59%
159
For 175
=
190
205
180
182
174.75
15.75
1.82
.50 173.18
173.36
16.64
= 54.05/8
=29.98
6.76%
175.02
178.02
1.98
178.22
3.78
82.45
MAD
10.31
MSE
190.82
Rounded
Forecast
with
= .50
175
177.50
172.75
165.88
170.44
180.22
192.61
186.30
Absolute
Deviation
for
= .50
5.00
9.50
13.75
9.12
19.56
24.78
12.61
4.30
98.62
12.33
195.24
4 44
Comparison of Forecast
Error
Quarter
Actual
Tonnage
Unloaded
Rounded
Forecast
with
= .10
1
2
3
4
5
6
7
8
180
168
159
175
190
205
180
182
175
175.5
174.75
173.18
173.36
175.02
178.02
178.22
MAD
MSE
MAPE
Absolute
Deviation
for
= .10
5.00
7.50
15.75
1.82
16.64
29.98
1.98
3.78
82.45
10.31
190.82
5.59%
Rounded
Forecast
with
= .50
175
177.50
172.75
165.88
170.44
180.22
192.61
186.30
Absolute
Deviation
for
= .50
5.00
9.50
13.75
9.12
19.56
24.78
12.61
4.30
98.62
12.33
195.24
6.76%
4 45
Exponentially
smoothed (Ft) + (Tt)
forecast
Exponentially
smoothed
trend
4 46
4 47
Actual
Demand (At)
Smoothed
Forecast, Ft
Smoothed
Trend, Tt
Forecast
Including
Trend, FITt
12
17
20
19
24
21
31
28
36
11
13.00
Table 4.1
2008 Prentice Hall, Inc.
4 48
Actual
Demand (At)
Smoothed
Forecast, Ft
Smoothed
Trend, Tt
Forecast
Including
Trend, FITt
12
17
20
19
24
21
31
28
36
11
13.00
Table 4.1
2008 Prentice Hall, Inc.
4 49
Actual
Demand (At)
Smoothed
Forecast, Ft
Smoothed
Trend, Tt
Forecast
Including
Trend, FITt
12
17
20
19
24
21
31
28
36
11
12.80
13.00
Table 4.1
2008 Prentice Hall, Inc.
4 50
Actual
Demand (At)
Smoothed
Forecast, Ft
Smoothed
Trend, Tt
12
17
20
19
24
21
31
28
36
11
12.80
2
1.92
Forecast
Including
Trend, FITt
13.00
Table 4.1
2008 Prentice Hall, Inc.
4 51
Actual
Demand (At)
Smoothed
Forecast, Ft
Smoothed
Trend, Tt
Forecast
Including
Trend, FITt
12
17
20
19
24
21
31
28
36
11
12.80
2.10
2.32
2.23
2.38
2.07
2.45
2.32
2.68
2
1.92
13.00
14.72
15.18
17.82
19.91
22.51
24.11
27.14
29.28
32.48
17.28
20.14
22.14
24.89
26.18
29.59
31.60
35.16
Table 4.1
2008 Prentice Hall, Inc.
4 52
Product demand
30
25
20
15
10
5
0
|
1
|
2
|
3
|
4
|
5
|
6
Time (month)
2008 Prentice Hall, Inc.
|
7
|
8
|
9
Figure 4.3
4 53
Trend Projections
Fitting a trend line to historical data points
to project into the medium to long-range
Linear trends can be found using the least
squares technique
y^ = a + bx
^
where y
= computed value of
the variable to be predicted
(dependent variable)
a
= y-axis intercept
b
= slope of the regression line
x
= the independent variable
4 54
Deviation7
Deviation5
Deviation3
Deviation4
Deviation1
(error)
Deviation2
Trend line, y^ = a + bx
Time period
2008 Prentice Hall, Inc.
Deviation6
Figure 4.4
4 55
Deviation7
Deviation5
Deviation3
Deviation1
Deviation2
Trend line, y^ = a + bx
Time period
2008 Prentice Hall, Inc.
Deviation6
Figure 4.4
4 56
xy - nxy
b=
x2 - nx2
a = y - bx
4 57
Time
Period (x)
1
2
3
4
5
6
7
x = 28
x=4
Electrical Power
Demand
74
79
80
90
105
142
122
y = 692
y = 98.86
x2
xy
1
4
9
16
25
36
49
x2 = 140
74
158
240
360
525
852
854
xy = 3,063
3,063 - (7)(4)(98.86)
xy - nxy
b=
=
= 10.54
140 - (7)(42)
x2 - nx2
a = y - bx = 98.86 - 10.54(4) = 56.70
2008 Prentice Hall, Inc.
4 58
Time
Period (x)
Electrical Power
Demand
x2
xy
1999
1
74
1
2000
2
79
4
line is 80
2001The trend
3
9
2002
4
90
16
2003
105
25
y^ 5= 56.70 + 10.54x
2004
6
142
36
2005
7
122
49
x = 28
y = 692
x2 = 140
x=4
y = 98.86
74
158
240
360
525
852
854
xy = 3,063
3,063 - (7)(4)(98.86)
xy - nxy
b = x2 - nx2 =
= 10.54
140 - (7)(42)
a = y - bx = 98.86 - 10.54(4) = 56.70
2008 Prentice Hall, Inc.
4 59
Power demand
160
150
140
130
120
110
100
90
80
70
60
50
Trend line,
y^ = 56.70 + 10.54x
|
2001
|
2002
|
2003
|
2004
|
2005
Year
|
2006
|
2007
|
2008
|
2009
4 60
The multiplicative
seasonal model
can adjust trend
data for seasonal
variations in
demand
4 62
4 63
Demand
2005 2006 2007
80
70
80
90
113
110
100
88
85
77
75
82
85
85
93
95
125
115
102
102
90
78
72
78
105
85
82
115
131
120
113
110
95
85
83
80
Average
2005-2007
Average
Monthly
90
80
85
100
123
115
105
100
90
80
80
80
94
94
94
94
94
94
94
94
94
94
94
94
Seasonal
Index
4 64
Demand
2005 2006 2007
Average
2005-2007
Average
Monthly
Jan
80
85 105
90
94
Feb
70
85
85
80
94
2005-2007
Mar
80
93 average
82
85 monthly demand
94
Seasonal index =
demand
Apr
90
95 115 average monthly
100
94
May
113 125= 90/94
131 = .957 123
94
Jun
110 115 120
115
94
Jul
100 102 113
105
94
Aug
88 102 110
100
94
Sept
85
90
95
90
94
Oct
77
78
85
80
94
Nov
75
72
83
80
94
Dec
82
78
80
80
94
2008 Prentice Hall, Inc.
Seasonal
Index
0.957
4 65
Demand
2005 2006 2007
80
70
80
90
113
110
100
88
85
77
75
82
85
85
93
95
125
115
102
102
90
78
72
78
105
85
82
115
131
120
113
110
95
85
83
80
Average
2005-2007
Average
Monthly
Seasonal
Index
90
80
85
100
123
115
105
100
90
80
80
80
94
94
94
94
94
94
94
94
94
94
94
94
0.957
0.851
0.904
1.064
1.309
1.223
1.117
1.064
0.957
0.851
0.851
0.851
4 66
Demand
2005 2006 2007
Average
2005-2007
Average
Monthly
80
85 105
90
94
for802008
70
85 Forecast
85
94
80
93
82
85
94
annual demand
= 1,200
90Expected
95 115
100
94
113 125 131
123
94
110 115 120 1,200 115
94
Jan
x .957 = 96
100 102 113 12
105
94
88 102 110 1,200 100
94
85
90
Feb 95
x90
.851 = 85 94
12
77
78
85
80
94
75
72
83
80
94
82
78
80
80
94
Seasonal
Index
0.957
0.851
0.904
1.064
1.309
1.223
1.117
1.064
0.957
0.851
0.851
0.851
4 67
140
130
Demand
120
110
100
90
80
70
|
J
|
F
|
M
|
A
|
M
|
J
|
J
|
A
|
S
|
O
|
N
|
D
Time
2008 Prentice Hall, Inc.
4 68
Inpatient Days
10,000
9,800
9,600
9,400
9573
9530
9551
9659
9616
9594
9637
9745
9702
9680
9724
9766
9,200
9,000
|
|
|
|
|
|
|
|
|
|
|
|
Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec
67 68 69 70 71 72 73 74 75 76 77 78
Month
Figure 4.6
4 69
1.06
1.04 1.04
1.02
1.02
1.00
0.94
0.92
1.01
1.00
0.99
0.98
0.96
1.03
1.04
0.98
0.99
0.97
0.97
0.96
|
|
|
|
|
|
|
|
|
|
|
|
Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec
67 68 69 70 71 72 73 74 75 76 77 78
Month
Figure 4.7
4 70
Inpatient Days
10,000
9,800
10068
9949
9911
9764
9,600
9572
9,400
9,200
9,000
9724
9691
9520 9542
9265
9411
9355
|
|
|
|
|
|
|
|
|
|
|
|
Jan Feb Mar Apr May June July Aug Sept Oct Nov Dec
67 68 69 70 71 72 73 74 75 76 77 78
Month
Figure 4.8
4 71
Associative Forecasting
Used when changes in one or more
independent variables can be used to predict
the changes in the dependent variable
Most common technique is linear
regression analysis
We apply this technique just as we did
in the time series example
4 72
Associative Forecasting
Forecasting an outcome based on predictor
variables using the least squares technique
y^ = a + bx
^
where y
= computed value of
the variable to be predicted
(dependent variable)
a
= y-axis intercept
b
= slope of the regression line
x
= the independent variable
though to predict the value of the
dependent variable
4 73
Associative Forecasting
Example
Local Payroll
($ billions), x
1
3
4
4.0
2
3.0
1
7
2.0
Sales
Sales
($ millions), y
2.0
3.0
2.5
2.0
2.0
3.5
1.0
|
1
|
2
|
|
|
|
3
4
5 6
Area payroll
|
7
4 74
Associative Forecasting
Example
Sales, y
2.0
3.0
2.5
2.0
2.0
3.5
y = 15.0
Payroll, x
x2
1
1
3
9
4
16
2
4
1
1
7
49
x = 18
x2 = 80
x = x/6 = 18/6 = 3
y = y/6 = 15/6 = 2.5
2008 Prentice Hall, Inc.
b=
xy
2.0
9.0
10.0
4.0
2.0
24.5
xy = 51.5
51.5 - (6)(3)(2.5)
xy - nxy
80 - (6)(32)
x2 - nx2 =
= .25
Associative Forecasting
Example
Sales
y^ = 1.75 + .25x
2.0
1.0
0
2008 Prentice Hall, Inc.
|
1
|
2
|
|
|
|
3
4
5 6
Area payroll
|
7
4 76
Sales
|
1
|
2
|
|
|
|
3
4
5 6
Area payroll
|
7
4 77
y
=
point
(y - yc)2
n-2
y-value of each data
yc
=
computed value of
the dependent variable, from the
regression equation
2008 Prentice Hall, Inc.
n
=
points
number of data
4 78
y2 - ay - bxy
n-2
4 79
y2 - ay - bxy
=
n-2
Sy,x = .306
4.0
Sales
3.25
3.0
2.0
1.0
0
2008 Prentice Hall, Inc.
|
1
|
2
|
|
|
|
3
4
5 6
Area payroll
|
7
4 80
Correlation
How strong is the linear
relationship between the
variables?
Correlation does not necessarily
imply causality!
Coefficient of correlation, r,
measures degree of association
Values range from -1 to +1
4 81
Correlation Coefficient
r=
n xy - x y
[n x2 - ( x)2][n y2 - ( y)2]
4 82
Correlation Coefficient
y
r=
n xy - x y
[n x2 - ( x)2][n y2 - ( y)2]
(b) Positive
correlation:
0<r<1
(c) No correlation:
r=0
2008 Prentice Hall, Inc.
Correlation
Coefficient of Determination, r2,
measures the percent of change in
y predicted by the change in x
Values range from 0 to 1
Easy to interpret
4 84
Multiple Regression
Analysis
If more than one independent variable is to be
used in the model, linear regression can be
extended to multiple regression to
accommodate several independent variables
^
y = a + b1x1 + b2x2
Computationally, this is quite
complex and generally done on the
computer
2008 Prentice Hall, Inc.
4 85
Multiple Regression
Analysis
In the Nodel example, including interest rates in
the model gives the new equation:
^ = 1.80 + .30x - 5.0x
y
1
2
An improved correlation coefficient of r = .96
means this model does a better job of predicting
the change in construction sales
Sales = 1.80 + .30(6) - 5.0(.12) = 3.00
Sales = $3,000,000
2008 Prentice Hall, Inc.
4 86
4 87
4 88
Tracking Signal
Signal exceeding limit
Tracking signal
+
0 MADs
Acceptable
range
4 89
1
2
3
4
5
6
90
95
115
100
125
140
Forecast
Demand
Error
RSFE
Absolute
Forecast
Error
100
100
100
110
110
110
-10
-5
+15
-10
+15
+30
-10
-15
0
-10
+5
+35
10
5
15
10
15
30
Cumulative
Absolute
Forecast
Error
MAD
10
15
30
40
55
85
10.0
7.5
10.0
10.0
11.0
14.2
4 90
1
2
3
4
5
6
Tracking
Actual Signal
Forecast
Demand
Demand Error
(RSFE/MAD)
RSFE
Absolute
Forecast
Error
90-10/10
100= -1 -10
95
-15/7.5
100= -2 -5
115 0/10
100
= 0 +15
100-10/10
110= -1 -10
125
+5/11110
= +0.5+15
140
+35/14.2
110= +2.5
+30
-10
-15
0
-10
+5
+35
10
5
15
10
15
30
Cumulative
Absolute
Forecast
Error
MAD
10
15
30
40
55
85
10.0
7.5
10.0
10.0
11.0
14.2
4 91
Adaptive Forecasting
Its possible to use the computer to
continually monitor forecast error and
adjust the values of the and
coefficients used in exponential
smoothing to continually minimize
forecast error
This technique is called adaptive
smoothing
2008 Prentice Hall, Inc.
4 92
Focus Forecasting
Developed at American Hardware Supply,
focus forecasting is based on two principles:
1. Sophisticated forecasting models are not
always better than simple ones
2. There is no single technique that should
be used for all products or services
This approach uses historical data to test
multiple forecasting models for individual items
The forecasting model with the lowest error is
then used to forecast the next demand
2008 Prentice Hall, Inc.
4 93
4 94
20%
15%
10%
5%
11-12
1-2
12-1
(Lunchtime)
2-3
3-4
4-5
5-6
7-8
6-7
(Dinnertime)
Hour of day
8-9
9-10
10-11
Figure 4.12
4 95
6
8
A.M.
10
12
Hour of day
6
8
P.M.
10
12
Figure 4.12
4 96