7. â˘Strategic Role of Forecasting in Supply
Chain Management
â˘Components of Forecasting Demand
â˘Time Series Methods
â˘Forecast Accuracy
â˘Time Series Forecasting Using Excel
â˘Regression Methods
12-576
Lecture Outline
9. â˘Quality Management
⢠Accurately forecasting customer demand
a key to providing good quality service
is
â˘Strategic Planning
⢠Successful strategic planning requires
accurate forecasts of future products and
markets
12-579
Forecasting
11. â˘Indicates how far into the future is
forecast
⢠Short- to mid-range forecast
â˘typically encompasses the immediate future
â˘daily up to two years
⢠Long-range forecast
â˘usually encompasses a period of time longer
than two years
12-581
Time Frame
12. ⢠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 periodically
12-582
Demand Behavior
14. ⢠Time series
⢠statistical techniques that use historical demand data
to predict future demand
⢠Regression methods
⢠attempt to develop a mathematical relationship
between demand and factors that cause its behavior
⢠Qualitative
⢠use management judgment, expertise, and opinion to
predict future demand
12-584
Forecasting Methods
15. â˘Management, marketing, purchasing,
and engineering are sources for internal
qualitative forecasts
â˘Delphi method
⢠involves soliciting forecasts about
technological advances from experts
12-585
Qualitative Methods
16. model that seems
No
Is accuracy of
12-586
acceptable?
planning horizon
and measure forecast
on additional qualitative
8b. Select new
adjust parameters of
Forecasting Process
1. Identify the 2. Collect historical 3. Plot data and identify
purpose of forecast data patterns
6. Check forecast 5. Develop/compute
accuracy with one or forecast for period of
more measures historical data
4. Select a forecast
appropriate for data
7.
forecast forecast model or
existing model
Yes
8a. Forecast over 9.Adjust forecast based 10. Monitor results
information and insight accuracy
17. ⢠Assume that what has occurred in the past will
continue to occur in the future
⢠Relate the forecast to only one factor - time
⢠Include
⢠moving average
⢠exponential smoothing
⢠linear trend line
12-587
Time Series
18. ⢠Naive forecast
⢠demand in current period is used as next periodâs
forecast
⢠Simple moving average
⢠uses average demand for a fixed sequence of
periods
⢠stable demand with no pronounced behavioral
patterns
⢠Weighted moving average
⢠weights are assigned to most recent data
12-588
Moving Average
19. FORECAST
MONTH PER MONTH
Feb 9
10
20
12-589
ORDERS
MONTH PER MONTH FORECA
Jan 120 -
Mar 100
90
Apr 7
15
00
May 110
75
June 5
10
10
July 750
Aug 130
75
Sept 110
30
Oct 9
10
10
90
Nov -
Moving Average:
NaĂŻve Approach
20. Simple Moving Average
Di
i = 1
12-590
n
MAn =
n
where
n = number of periods in
the moving average
Di = demand in period i
Simple Moving Aver
21. 3-month Simple Moving Average
3
ORDERS MOVING
A
VERAGE
Di
MONTH
Jan
Feb
PER MONTH
120
90
i = 1
MA3 =
â
â
3
Mar
Apr
May
June
July
Aug
Sept
Oct
Nov
100
75
110
50
75
130
110
90
-
â
103.3
88.3
95.0
78.3
78.3
85.0
105.0
110.0
90 + 110
3
+ 130
=
= 110 orders
for Nov
12-591
3-month Simple Moving
22. 5-month Simple Moving Average
ORDERS MOVING
A
VERAGE 5
MONTH
Jan
Feb
PER MONTH
120
90
Di
â
â
i = 1
MA5 =
5
Mar
Apr
May
June
July
Aug
Sept
Oct
Nov
100
75
110
50
75
130
110
90
-
â
â
â
99.0
85.0
82.0
88.0
95.0
91.0
90 + 110 + 130+75+50
= 5
= 91 orders
for Nov
12-592
5-month Simple Moving
23. 25 â
12-593
Orders
Smoothing Effects
150 â
125 â 5-month
100 â
75 â
50 â 3-month
Actual
0 â | | | | | | | | | | |
Jan Feb Mar Apr May June July Aug Sept Oct Nov
Month
24. Weighted Moving Average
n
Wi Di
Adjusts moving average
method to more
closely reflect data
fluctuations
WMAn =
i = 1
where
Wi = the weight for period i,
between 0 and
percent
100
Wi = 1.00
12-594
Weighted Moving Ave
25. Weighted Moving Average Example
October 50% 90
i = 1
12-595
MONTH WEIGHT DATA
August 17% 130
September 33% 110
3
November Forecast WMA3 = Wi Di
= (0.50)(90) + (0.33)(110) + (0.17)(130)
= 103.4 orders
26. y = a + bx
where
a = intercept
b = slope of the line
x = time period
y = forecast for
demand for period x
n
y = = mean of the y values
n
12-606
xy - nxy
x2 - nx2 b =
a = y - b x
where
n = number of periods
x =
x
= mean of the x values
y
Linear Trend Line
28. Least Squares Example
12
y = = 46.42
12
b = = =1.72
12-608
78
x = = 6.5
557
ďĽxy - nxy 3867 - (12)(6.5)(46.42)
ďĽx2 - nx2 650 - 12(6.5)2
a = y - bx
= 46.42 - (1.72)(6.5) = 35.2
Least Squares Exam
(cont.)
29. Period
0 â
12-609
Demand
Linear trend line y = 35.2 + 1.72x
Forecast for period 13 y = 35.2 + 1.72(13) = 57.56 units
70 â
60 â
Actual
50 â
40 â
Linear trend line
30 â
20 â
10 â | | | | | | | | | | | | |
1 2 3 4 5 6 7 8 9 10 11 12 13
30. Statistical Control Charts
ďĽ(Dt - Ft)2
= n - 1
Using we can calculate statistical control
limits for the forecast error
Control limits are typically set at 3
12-621
Statistical Control Ch
32. Time Series Forecasting using Excel
â˘Excel can be used to develop forecasts:
⢠Moving average
⢠Exponential smoothing
⢠Adjusted exponential
⢠Linear trend line
smoothing
12-623
Time Series Forecasting
33. y = a + bx a = y - b x
xy - nxy
b =
x2 - nx2
where
a = intercept
b = slope of the line
x
x = n = mean of the x data
y
y = n = mean of the y data
12-630
Linear Regression
35. Linear Regression Example (cont.)
8
8
= 4.06
12-632
49
x = = 6.125
346.9y = = 43.36
ďĽxy - nxy2
b =
ďĽx2 - nx2
(2,167.7) - (8)(6.=
125)(43.36)
(311) - (8)(6.125)2
a = y - bx
= 43.36 - (4.06)(6.125)
= 18.46
Linear Regression Exam
36. 6
60
0,
,0
00
00
0 â
Wins, x
12-633
Attendance,
y
Linear Regression Example (cont.)
Regression equation Attendance forecast for 7 wins
y = 18.46 + 4.06x y = 18.46 + 4.06(7)
= 46.88, or 46,880
50,000 â
40,000 â
30,000 â
Linear regression line,
20,000 â y = 18.46 + 4.06x
10,000 â
| | | | | | | | | |
|
0 1 2 3 4 5 6 7 8 9 10
37. 12-639
Multiple Regression
Study the relationship of demand to two or more independent
variables
y = 0 + 1x1 + 2x2 ⌠+ kxk
where
0 = the intercept
1, ⌠, k = parameters for the
independent variables
x1, ⌠, xk = independent variables