Professional Documents
Culture Documents
Forecasting Outline
Introduction
Forecasting
Process
Forecasting Methods
Forecast Accuracy and Control
Forecast Method Selection and Usage
Introduction
A forecast
is a statement of future,
is a basis for planning,
is not for forecasting demand only,
requires a skillful blending of art and science,
assumes that the underlying system will
continue to exist in the future, and
is rarely perfect.
Forecasting Process
The forecast
Additional Properties
Timely
Reliable
ul
f
ng
i
n
ea
M
Accurate
Written
sy
a
E
to
e
us
Forecasting Methods
Basic
Methods
Judgmental Forecast
Statistical (Time Series) Forecast
Trend
Seasonality
Cycle
Association
Forecast
Statistical (Time Series) Forecast
Averaging
Weighted Moving Average
Exponential Smoothing
Judgmental Forecast
Executive opinions.
Mostly for long-range planning and introduction of new products. The view of one
person may prevail.
Unable to distinguish between what customers would like to do and what they
will actually do.
Could overly influenced by recent sales experiences. Low sales could lead to
low estimates.
Conflict of interest. Low sales estimates lead to better sales performance.
Data patterns:
Trend
A long term upward or downward movement in data.
Seasonality
Short-term regular variations related to weather, holiday, or other factors.
Cycle
Wavelike variation lasting more than one year.
Irregular Variation
Caused by unusual circumstances, not reflective of typical behavior.
Random variation
Residual variation after all other behaviors are accounted for.
Data Patterns
Irregular
variation
Trend
Cycles
90
89
88
Seasonal variations
Yt yt 1
No cost.
Quick and easy to prepare.
Easy to understand.
Can be applied to data with seasonality and trend
Yt yt 1 ct
MAn
y
i 1
or MAn wi yi
i 1
b)
40 41 39
40.00
3
Period
1
2
3
4
5
6
7
Demand
42
40
43
40
41
? 41.33 39
? 40.00
b)
Period
1
2
3
4
5
6
7
Demand
42
40
43
40
41
? 41.0 39
? 40.2
Exponential Smoothing
Yt yt 1 (d t 1 yt 1 )
Properties of Exponential
Smoothing
Exponential Smoothing
Example
Use exponential smoothing to
develop a series of forecasts
for the data, and compute
(actual-forecast)=error for
each period.
a)
b)
c)
Period (t)
Actual
42
40
43
40
41
39
46
44
45
10
38
11
40
12
Exponential Smoothing
Example
alpha=.10
Period (t)
Actual
Forecast
alpha=.40
Error
Forecast
Error
42.00
40.00
42.00
-2.00
42.00
-2.00
43.00
41.80
1.20
41.20
1.80
40.00
41.92
-1.92
41.92
-1.92
41.00
41.73
-0.73
41.15
-0.15
39.00
41.66
-2.66
41.09
-2.09
46.00
41.39
4.61
40.25
5.75
44.00
41.85
2.15
42.55
1.45
45.00
42.07
2.93
43.13
1.87
10
38.00
42.36
-4.36
43.88
-5.88
11
40.00
41.92
-1.92
41.53
-1.53
12
41.73
40.92
Linear Trend
Trend-Adjusted Exponential Smoothing
Seasonality
Cycle
Association
Linear Trend
Yt a bt
t 1
t 1
t 1
n tyt t yt
n
n t
t 1
t 1
y
t 1
b t
t 1
y bt
Week
Unit Sales
700
724
720
728
740
742
758
750
770
10
775
11
12
t 55
t 1
10
385
t 1
7.51
10(385) 55(55)
825
7,407 7.51(55)
699.40
10
Seasonality
Cycle
Associative Forecasts
High correlation of a
forecast with leading
variables can be useful
in computing the
forecast.
The simple linear
regression is the
simplest and most
widely used method.
Y a bX
n
b
x y
i
i 1
i 1
y
i 1
x
i
x y
i 1
x
i 1
i 1
2
b xi
i 1
y bx
Sales, X
Profits, Y
0.15
0.10
0.13
0.15
14
0.25
15
0.27
16
0.24
12
0.20
14
0.27
20
0.44
15
0.34
0.17
xy
x^2
y^2
0.15
1.05
49
0.0225
0.10
0.20
0.0100
0.13
0.78
36
0.0169
0.15
0.60
16
0.0225
14
0.25
3.50
196
0.0625
15
0.27
4.05
225
0.0729
16
0.24
3.84
256
0.0576
12
0.20
2.40
144
0.0400
14
0.27
3.78
196
0.0729
20
0.44
8.80
400
0.1936
15
0.34
5.10
225
0.1156
0.17
1.19
49
0.0289
132
2.71
35.29
1796
0.7159
n xy x y
n x2 x
12(35.29) 132(2.71)
0.01593
12(1796) 132(132)
y b x
n
2.71 0.01593(132)
0.0506
12
Y 0.0506 0.01593 X
Y 0.2099 (million $) for X 10
An Important Measure of
Simple Linear Regression
n xy x y
n x 2 x n y 2 y
2
20 41
17
35
25 31
38
50
9 10
15
11
19 14
Unemployment % 7.2 4.0 7.3 5.5 6.8 6.0 5.4 3.6 8.4 7.0 9.0
(3-month lag)
xy
x^2
y^2
7.2
20
144.0
51.8
400
4.0
41
164.0
16.0
1681
7.3
17
124.1
53.3
289
5.5
35
192.5
30.3
1225
6.8
25
170.0
46.2
625
6.0
31
186.0
36.0
961
5.4
38
205.2
29.2
1444
3.6
50
180.0
13.0
2500
8.4
15
126.0
70.6
225
7.0
19
133.0
49.0
361
9.0
14
126.0
81.0
196
70.2
305
1750.8
476.3
9907
n xy x y
n x2 x
11(1750.8) 70.2(305)
6.91
11(476.4) 70.2(70.2)
y b x
n
305 ( 6.91)(70.2)
71.85
11
Y 71.85 6.91X
r
n xy x y
n x2 x n y 2 y
2
11(1750.8) 70.2(305)
11(476.4) (70.2) 2 11(9907) (305) 2
0.966
Linear Regression
Assumptions
No
Forecast Accuracy
Error
Mean
Forecast Accuracy:
MAD & MSE
Actual forecast
MAD =
n
2
(Actual forecast)
MSE =
n-1
Example 10 (page 97).
Forecast Control
It is necessary to monitor forecast errors to ensure
that the forecast is performing adequately over
time. This is generally accomplished by comparing
forecast errors to predefined values, or action
limits.
Signal
Control Chart
tracking signal
yt
MAD
s MSE
Most important
Cost
Accuracy
Need to consider
Historical performance
Ability to respond to
change