Professional Documents
Culture Documents
Forecast
Forecast
+ =
+
+ +
=
+ + + =
t
n t i
i t
n t t t t
D
n
F
D D D
n
F
1
1
1 1 1
1
) (
1
+ + + =
+ + + =
2 1
2
2
1
) 1 ( ) 1 (
) 1 ( ) 1 (
t t t t
t t t t
D a D D F
D D D F
o o o o
o o o o o
Exponential Smoothing: Math
1
) 1 (
+ =
t t t
F a aD F
| |
+ + + =
+ + + =
2 1
2
2
1
) 1 ( ) 1 (
) 1 ( ) 1 (
t t t t
t t t t
D a D D F
D D D F
o o o o
o o o o o
Exponential Smoothing: Math
Thus, new forecast is weighted sum of old forecast and actual
demand
Notes:
- Only 2 values (D
t
and F
t-1
) are required, compared with n for moving
average
- Parameter a determined empirically (whatever works best)
- Rule of thumb: o < 0.5
- Typically, o = 0.2 or o = 0.3 work well
Forecast for k periods into future is:
1
2
2
1
) 1 (
) 1 ( ) 1 (
+ =
+ + + =
t t t
t t t t
F a aD F
D a a D a a aD F
t k t
F F =
+
Exponential Smoothing
Internet Unicycle Sales (1000's)
0
50
100
150
200
250
300
350
400
450
Jan-03 May-04 Sep-05 Feb-07 Jun-08 Nov-09 Mar-11 Aug-12
Month
U
n
i
t
s
o = 0.2
Example:
Exponential Smoothing
Complicating Factors
Simple Exponential Smoothing works well
with data that is moving sideways
(stationary)
Must be adapted for data series which
exhibit a definite trend
Must be further adapted for data series
which exhibit seasonal patterns
Holts Method:
Double Exponential Smoothing
What happens when there is a definite trend?
A trendy clothing boutique has had the following sales
over the past 6 months:
1 2 3 4 5 6
510 512 528 530 542 552
480
490
500
510
520
530
540
550
560
1 2 3 4 5 6 7 8 9 10
Month
Demand
Actual
Forecast
Holts Method:
Double Exponential Smoothing
Ideas behind smoothing with trend:
- ``De-trend'' time-series by separating base from trend effects
- Smooth base in usual manner using o
- Smooth trend forecasts in usual manner using |
Smooth the base forecast B
t
Smooth the trend forecast T
t
Forecast k periods into future F
t+k
with base and trend
) )( 1 (
1 1
+ + =
t t t t
T B D B o o
1 1
) 1 ( ) (
+ =
t t t t
T B B T | |
t t k t
kT B F + =
+
ES with Trend
Internet Unicycle Sales (1000's)
0
50
100
150
200
250
300
350
400
450
Jan-03 May-04 Sep-05 Feb-07 Jun-08 Nov-09 Mar-11 Aug-12
Month
U
n
i
t
s
o = 0.2, | = 0.4
Example:
Exponential Smoothing
with Trend
Winters Method:
Exponential Smoothing
w/ Trend and Seasonality
Ideas behind smoothing with trend and seasonality:
- De-trend: and de-seasonalizetime-series by separating base from
trend and seasonality effects
- Smooth base in usual manner using o
- Smooth trend forecasts in usual manner using |
- Smooth seasonality forecasts using
Assume m seasons in a cycle
- 12 months in a year
- 4 quarters in a month
- 3 months in a quarter
- et cetera
Winters Method:
Exponential Smoothing
w/ Trend and Seasonality
Smooth the base forecast B
t
Smooth the trend forecast T
t
Smooth the seasonality forecast S
t
) )( 1 (
1 1
+ + =
t t
m t
t
t
T B
S
D
B o o
1 1
) 1 ( ) (
+ =
t t t t
T B B T | |
m t
t
t
t
S
B
D
S
+ = ) 1 (
Winters Method:
Exponential Smoothing
w/ Trend and Seasonality
Forecast F
t
with trend and seasonality
Smooth the trend forecast T
t
Smooth the seasonality forecast S
t
m k t t t k t
S kT B F
+ +
+ = ) (
1 1
1 1
) 1 ( ) (
+ =
t t t t
T B B T | |
m t
t
t
t
S
B
D
S
+ = ) 1 (
ES with Trend and Seasonality
Internet Unicycle Sales (1000's)
0
50
100
150
200
250
300
350
400
450
500
Jan-03 May-04 Sep-05 Feb-07 Jun-08 Nov-09 Mar-11 Aug-12
Month
U
n
i
t
s
o = 0.2, | = 0.4, = 0.6
Example:
Exponential Smoothing
with
Trend and Seasonality
Forecasting Performance
Mean Forecast Error (MFE or Bias): Measures
average deviation of forecast from actuals.
Mean Absolute Deviation (MAD): Measures
average absolute deviation of forecast from
actuals.
Mean Absolute Percentage Error (MAPE):
Measures absolute error as a percentage of the
forecast.
Standard Squared Error (MSE): Measures
variance of forecast error
How good is the forecast?
Forecasting Performance Measures
) (
1
1
t
n
t
t
F D
n
MFE =
=
=
=
n
t
t t
F D
n
MAD
1
1
=
n
t
t
t t
D
F D
n
MAPE
1
100
2
1
) (
1
t
n
t
t
F D
n
MSE =
=
Want MFE to be as close to zero as possible --
minimum bias
A large positive (negative) MFE means that the
forecast is undershooting (overshooting) the actual
observations
Note that zero MFE does not imply that forecasts are
perfect (no error) -- only that mean is on target
Also called forecast BIAS
Mean Forecast Error (MFE or Bias)
) (
1
1
t
n
t
t
F D
n
MFE =
=
Mean Absolute Deviation (MAD)
Measures absolute error
Positive and negative errors thus do not cancel out (as
with MFE)
Want MAD to be as small as possible
No way to know if MAD error is large or small in
relation to the actual data
=
=
n
t
t t
F D
n
MAD
1
1
Mean Absolute Percentage Error
(MAPE)
Same as MAD, except ...
Measures deviation as a percentage of actual data
=
n
t
t
t t
D
F D
n
MAPE
1
100
Mean Squared Error (MSE)
Measures squared forecast error -- error variance
Recognizes that large errors are disproportionately more
expensive than small errors
But is not as easily interpreted as MAD, MAPE -- not as
intuitive
2
1
) (
1
t
n
t
t
F D
n
MSE =
=
Fortunately, there is software...