n
i =1
x
i
)(
n
i =1
y
i
)
n
n
i =1
x
2
i
-
(
n
i =1
x
i
)
2
=
S
xy
S
xx
a =
n
i =1
y
i
-b
n
i =1
x
i
n
= y-bx
- 13 -
Quantitative Forecasting Methods.
[Other Resource]
Various Forecasting Methods.
Quantitative Methods : Moving Average.
An arithmetic average of a certain number
n
of the most recent observations.
As each new observation is added, the oldest observation is dropped. The value
of
n
(the number of periods to use for the average) reflects responsiveness
versus stability in the same way that the choice of smoothing constant does in
exponential smoothing.
Example.
Demand over the past three months has been 120, 135, and
114 units. Using a three-moving average, calculate the forecast for the
fourth month.
Forecast for month 4 =
120 + 135 + 114
=
369
= 123
3 3
- 14 -
Quantitative Forecasting Methods.
[Other Resource]
Various Forecasting Methods.
Quantitative Methods : Moving Average.
- 15 -
Quantitative Forecasting Methods.
[Other Resource]
Quantitative Techniques.
Quantitative Methods : Weighted Moving Average.
Whereas the simple moving average gives equal weight to each component of
moving average database, a weighted moving average allows any weights to be
placed on each element, providing, of course, that the sum of all weights
equals 1.
F
t
=w
1
A
t -1
+w
2
A
t -2
+.....+w
n
A
t -n
where w
i
= Weight to be given to the actual occurrence for the period
t-n
n
= Total number of periods in the forecast.
n
i=1
=1
, The sum of all the weight must equal 1.
- 16 -
Quantitative Forecasting Methods.
[Other Resource]
Quantitative Techniques.
Quantitative Methods : Exponential Smoothing.
A type of weighted moving average forecasting techniques in which past
observations are geometrically discounted according to their age. The heaviest
weight is assigned to the most recent data.
The techniques makes use of a smoothing constant to apply the difference
between the most recent forecast and the critical sales data.
F
t
= A
t -1
+ ( 1-) F
t -1
where
F
t
= New forecast.
A
t -1
= Latest demand.
F
t -1
= Previous forecast.
= Smoothing factor. (0
1)
- 17 -
Quantitative Forecasting Methods.
[Other Resource]
Quantitative Techniques.
Quantitative Methods : Exponential Smoothing.
- 18 -
Quantitative Forecasting Methods.
[Other Resource]
Quantitative Techniques.
Quantitative Methods : Exponential Smoothing.
- 19 -
Quantitative Forecasting Methods.
[Other Resource]
Quantitative Techniques.
Quantitative Methods : Trend Effects in Exponential Smoothing.
An upward or downward trend in data collected over a sequence of time periods
causes the exponential forecast to always lad behind (be above or below) the
actual occurrence.
To correct the trend, smoothing constant delta (
( A
t
-F
t
)
n
Mean Absolute Deviation (MAD), Standard Deviation.
- The average of the absolute values of the deviations of observed values
from some expected value.
MAD=
A
t
-F
t
n
or MAD
t
=MAD
t -1
+A
t
-F
t
- 28 -
Forecasting Management.
[Other Resource]
Tracking The Forecast.
Example.
Period Forecast Actual
Error
(Actual - Forecast)
Absolute
Error
Error
Squared
1 1000 1200 200 200 40000
2 1000 1000 0 0 0
3 1000 800 -200 200 40000
4 1000 900 -100 100 10000
5 1000 1400 400 400 160000
6 1000 1200 200 200 40000
7 1000 1100 100 100 10000
8 1000 700 -300 300 90000
9 1000 1000 0 0 0
10 1000 900 -100 100 10000
Total 10000 12000 200 1600 4000000
Cumulative Sum of Error = (A
t
-F
t
) = 200.
Bias = Cumulative Sum of Error / Number of periods = 200/10 = 20.
MAD = Sum of Absolute Error / Number of periods = 1600/10 = 160.
Standard Deviation (SD) = 1.25 MAD
- 29 -
Forecasting Management.
[Other Resource]
Tracking The Forecast.
Tracking Signals.
The ratio of the cumulative algebraic sum of the deviation between the forecasts
and the actual values to the mean absolute deviation. It used to signal when the
validity of the forecasting model might be in doubt.
Tracking Signal =
Cumulative Sum of Error
MAD
Tracking Signal vs. MAD
Period Forecast Actual MAD
Cumulative
Sum of Error
Tracking Signal
1 1000 800 200 - 200 - 1
2 1000 800 200 - 400 - 2
3 1000 1200 200 - 200 - 1
4 1000 1200 200 0 0
5 1000 1200 200 200 1
6 1000 1200 200 400 2
7 1000 1200 200 600 3
8 1000 1200 200 800 4
- 30 -
Performance Check.
1. Forecasts are most useful if they are based on
A. Quantitative factors.
B. Qualitative factors.
C. Both quantitative and qualitative factors.
D. Neither qualitative nor quantitative factors.
2. Which of the following statements is TRUE about the integration of planning systems
and the level of forecast accuracy ?
A. They are independent.
B. The planning system should include information on the level of forecast accuracy.
C. Forecast accuracy is implied in the planning process system.
D. Once the data are input into the planning system they do not change.
- 31 -
Performance Check.
3. Which of the following is MOST directly affected by forecast inaccuracy ?
A. Capacity. B. Quality. C. Budget. D. Planning.
4. Which of the following is a qualitative method of forecasting ?
A. Expert opinion. B. Historical data.
C. Exponential smoothing. D. Moving average.
5. Seasonality is demand that shows which of the following patterns ?
A. Repetitive pattern over some time interval.
B. General movement up or down over time.
C. Repetitive pattern based on economic conditions.
D. Repetitive pattern based on promotional activity.
- 32 -
Performance Check.
6. Which of the following depend on external conditions affecting on demand ?
A. Sales promotions. B. Product life cycle.
C. Economic cycle. D. Product price policy.
7. Given the following information, calculate the new forecast for Product A using
exponential smoothing.
Alpha factor - 0.7
Actual Demand - 600.
Old Forecast - 562.
Seasonal Index - 2.1
A. 813. B. 882. C. 1260. D. 589.
- 33 -
Performance Check.
8. Which of the following is the BEST statement about the general principles of
forecasting ?
A. Forecasting are more accurate for individual items than for groups of items.
B. Forecasting are more accurate for distant periods of time.
C. Every forecast should include an estimate of error.
D. Forecasts are usually accurate.
9. Why is important to track the forecast ?
A. To compare the actual sales with the forecast.
B. To improve our forecasting methods.
C. To utilize actual sales data.
D. To satisfy marketing's need to know.
- 34 -
Performance Check.
10. Which of the following statement is MOST accurate ?
A. If we wish to forecast demand, past sales must be used for the forecast.
B. Forecasts made in dollars for total sales should be used by manufacturing.
C. Forecasts should be made for individual items in a group.
D. The circumstances relating to demand data should be recorded.
- 35 -
Performance Check.
Solutions.
1 2 3 4 5 6 7 8 9 10
C B D A A C D C B D