forecasting calc
TRANSCRIPT
-
8/10/2019 Forecasting Calc
1/64
-
8/10/2019 Forecasting Calc
2/64
-
8/10/2019 Forecasting Calc
3/64
SAP AG 2002, Title of Presentation, Speaker Name / 3
Overview of Forecasting in APO
3
33
1
11
Univariate Forecast Basics
2
22 History
4
44 Univariate Models in APOModels in APOModels in APOModels in APO
5
55 Forecast Error Analysis
6
66
7
77
Master Forecast Profile Setup
Forecast Execution
Overview of the Forecasting Workshop
-
8/10/2019 Forecasting Calc
4/64
SAP AG 2002, Title of Presentation, Speaker Name / 4
333 Univariate Forecast Basics
444 Univariate Models in APOModels in APOModels in APOModels in APO
555 Forecast Error Analysis
What we will talk about today
-
8/10/2019 Forecasting Calc
5/64
SAP AG 2002, Title of Presentation, Speaker Name / 5
333 Univariate Forecast Basics
444 Univariate Models in APOModels in APOModels in APOModels in APO
555 Forecast Error Analysis
-
8/10/2019 Forecasting Calc
6/64
SAP AG 2002, Title of Presentation, Speaker Name / 6
Elements of the Univariate Forecast
Actual Value
Basic Value
Trend Value
Seasonal Index
Length of Season
Initialization
Ex-post Forecast
Forecast
Parameters
Exceptions are models 13, 14, 35, 70, 80, 94
-
8/10/2019 Forecasting Calc
7/64
SAP AG 2002, Title of Presentation, Speaker Name / 7
Actual Value
DataValues
Past Horizon
Historical values used as the basis of theforecast
-
8/10/2019 Forecasting Calc
8/64
SAP AG 2002, Title of Presentation, Speaker Name / 8
Basic Value
DataValues
Forecast Horizon
Basic Value - Controls Vertical Placement
1
22000
1000
-
8/10/2019 Forecasting Calc
9/64
SAP AG 2002, Title of Presentation, Speaker Name / 9
Trend Value
DataValues
Forecast Horizon
Trend - Slope of line
1
2.75
-.75
-
8/10/2019 Forecasting Calc
10/64
SAP AG 2002, Title of Presentation, Speaker Name / 10
Seasonal Index
DataValues
Forecast Horizon
Seasonal index - Divergence from Basic Value
1.00
2.50
.25
-
8/10/2019 Forecasting Calc
11/64
SAP AG 2002, Title of Presentation, Speaker Name / 11
Length of Season
DataValues
Number of Periods in the SeasonTypically = one year
Season
-
8/10/2019 Forecasting Calc
12/64
SAP AG 2002, Title of Presentation, Speaker Name / 12
Initialization
Basic value, Trend value, Seasonal indices, and the MeanAbsolute Deviation are initialized.
-
8/10/2019 Forecasting Calc
13/64
SAP AG 2002, Title of Presentation, Speaker Name / 13
Ex-post Forecast
An Ex post Forecast is a forecast run in the past for comparisonAn Ex post Forecast is a forecast run in the past for comparisonAn Ex post Forecast is a forecast run in the past for comparisonAn Ex post Forecast is a forecast run in the past for comparisonagainst historical values. The exagainst historical values. The exagainst historical values. The exagainst historical values. The ex----post forecast is used to measurepost forecast is used to measurepost forecast is used to measurepost forecast is used to measure
model fit.model fit.model fit.model fit.
Data
Values
Future
Forecast
History
Initialization Ex-post Forecast
History Values
ForecastValues
- Initialization length is dependent on the forecast model- Ex-post forecast length is the history horizon less the
initialization horizon
-
8/10/2019 Forecasting Calc
14/64
SAP AG 2002, Title of Presentation, Speaker Name / 14
Ex-post Forecast
The following Models do not generate an ExThe following Models do not generate an ExThe following Models do not generate an ExThe following Models do not generate an Ex----post forecast:post forecast:post forecast:post forecast:
Manual forecastManual forecastManual forecastManual forecast
Historical data adoptedHistorical data adoptedHistorical data adoptedHistorical data adopted
Weighted moving averageWeighted moving averageWeighted moving averageWeighted moving average
Moving averageMoving averageMoving averageMoving average
70707070
60606060
14141414
13131313
-
8/10/2019 Forecasting Calc
15/64
SAP AG 2002, Title of Presentation, Speaker Name / 15
General Calculation
Basic(t), trend(t), seasonal(t)
=
Function(actual(t), basic(t-1), trend(t-1), seasonal(t-1s))
Forecast = Function(basic(t), trend(t), seasonal(t))
-
8/10/2019 Forecasting Calc
16/64
-
8/10/2019 Forecasting Calc
17/64
SAP AG 2002, Title of Presentation, Speaker Name / 17
Period 1 2 3 4 5 6 7 1 2 3 4
History 80 95 100 115 125 110 110
G - Basic Value 102 113
T - Trend 10.0 10.3
EX Ex-post 112 123
F Forecast
History Horizon Forecast Horizon
Trend Model Example Calculate New Basic and Trend
Trend Value T(t) = [ G(t) - G(t-1) ] + (1-)T(t-1)
10.3 = .3 [ 113 102 ] + (.7) 10.0
Basic Value G(t) = V(t) + (1-) [ G(t-1) + T(t-1) ]
113 = .3 (115) + (.7) [ 102 + 10.0 ]
Ex-Post Forecast Ex(t +i) = G(t) + i * T(t)Where i = 1
123 = 113 + 10.3
-
8/10/2019 Forecasting Calc
18/64
SAP AG 2002, Title of Presentation, Speaker Name / 18
Period 1 2 3 4 5 6 7 1 2 3 4
History 80 95 100 115 125 110 110
G - Basic Value 102 113
T - Trend 10.0 10.3
EX Ex-post 112 123
F Forecast
History Horizon Forecast Horizon
Trend Model Example Calculation Repeated
Ex-Post Forecast Ex(t +i) = G(t) + i * T(t)Where i = 1
124 127
10.5 8.3
123 134 135
124
10.5
123 134
124 127 128
10.5 8.3 6.1
123 134 135
134
Forecast P(t+i) = G(t) + i * T(t)
Basic Value G(t) = V(t) + (1-) [ G(t-1) + T(t-1) ]
Trend Value T(t) = [ G(t) - G(t-1) ] + (1-)T(t-1)
-
8/10/2019 Forecasting Calc
19/64
SAP AG 2002, Title of Presentation, Speaker Name / 19
Period 1 2 3 4 5 6 7 1 2 3 4
History 80 95 100 115 125 110 110
G - Basic Value 102 113 124 127 128 128
T - Trend 10.0 10.3 10.5 8.3 6.1 6.1
EX Ex-post 112 123 134 135
F Forecast 134 140
History Horizon Forecast Horizon
Trend Model Example Calculation Repeated
Ex-Post Forecast Ex(t +i) = G(t) + i * T(t)Where i = 1
Forecast P(t+i) = G(t) + i * T(t)
110
128 128 128
6.1 6.1 6.1
135
134 140 146
1
110
128 128 128 128
6.1 6.1 6.1 6.1
135
134 140 146 152
2
Basic Value G(t) = V(t) + (1-) [ G(t-1) + T(t-1) ]
Trend Value T(t) = [ G(t) - G(t-1) ] + (1-)T(t-1)
-
8/10/2019 Forecasting Calc
20/64
SAP AG 2002, Title of Presentation, Speaker Name / 20
Model parameters
The model parameters, Alpha, Beta, and Gamma, control theweighting of each historical values.
Alpha is used in the basic value calculation
Beta is used in trend value calculation
Gamma is used in the Seasonal index calculation
The value for the parameters range from 0 to 1. A higher value will
place more emphasis on recent history.
The parameters also control how reactive the forecast is to changes inhistorical patterns.
-
8/10/2019 Forecasting Calc
21/64
SAP AG 2002, Title of Presentation, Speaker Name / 21
333 Univariate Forecast Basics
444 Univariate Models in APOModels in APOModels in APOModels in APO
555 Forecast Error Analysis
-
8/10/2019 Forecasting Calc
22/64
SAP AG 2002, Title of Presentation, Speaker Name / 22
Univariate Forecasting Models
Constant ModelsConstant ModelsConstant ModelsConstant Models
Moving Average ModelsMoving Average ModelsMoving Average ModelsMoving Average Models
Trend ModelsTrend ModelsTrend ModelsTrend Models
Seasonal ModelsSeasonal ModelsSeasonal ModelsSeasonal Models
Seasonal Trend ModelsSeasonal Trend ModelsSeasonal Trend ModelsSeasonal Trend Models
Automatic Model Selection I and IIAutomatic Model Selection I and IIAutomatic Model Selection I and IIAutomatic Model Selection I and II
Sporadic DemandSporadic DemandSporadic DemandSporadic Demand
Historical Data ModelHistorical Data ModelHistorical Data ModelHistorical Data Model
Linear RegressionLinear RegressionLinear RegressionLinear Regression
User ExitUser ExitUser ExitUser Exit
C M d l
-
8/10/2019 Forecasting Calc
23/64
SAP AG 2002, Title of Presentation, Speaker Name / 23
Constant Models
3 models within the constant model group:3 models within the constant model group:3 models within the constant model group:3 models within the constant model group:
Constant Model (10)Constant Model (10)Constant Model (10)Constant Model (10)
1111stststst Order Exponential Smoothing (11)Order Exponential Smoothing (11)Order Exponential Smoothing (11)Order Exponential Smoothing (11)
Constant Model with automatic Alpha adaptation (12)Constant Model with automatic Alpha adaptation (12)Constant Model with automatic Alpha adaptation (12)Constant Model with automatic Alpha adaptation (12)
Constant Models follow the pattern:Constant Models follow the pattern:Constant Models follow the pattern:Constant Models follow the pattern:
Same Formula !10 = 11
C t t M d l 1st d E ti l S thi (10 11)
-
8/10/2019 Forecasting Calc
24/64
SAP AG 2002, Title of Presentation, Speaker Name / 24
Constant Model 1st order Exponential Smoothing (10,11)
Use this model when there are no seasonal variations or trendUse this model when there are no seasonal variations or trendUse this model when there are no seasonal variations or trendUse this model when there are no seasonal variations or trendpatterns. Alpha parameter controls the weighting of history inpatterns. Alpha parameter controls the weighting of history inpatterns. Alpha parameter controls the weighting of history inpatterns. Alpha parameter controls the weighting of history in
determining the basic value.determining the basic value.determining the basic value.determining the basic value.
Basic value and exBasic value and exBasic value and exBasic value and ex----post forecast are equalpost forecast are equalpost forecast are equalpost forecast are equal
Higher alpha puts more weight on recent valuesHigher alpha puts more weight on recent valuesHigher alpha puts more weight on recent valuesHigher alpha puts more weight on recent values
Higher alpha makes the forecast more reactive to recent changesHigher alpha makes the forecast more reactive to recent changesHigher alpha makes the forecast more reactive to recent changesHigher alpha makes the forecast more reactive to recent changes inininin
historyhistoryhistoryhistory
E l f C t t M d l
-
8/10/2019 Forecasting Calc
25/64
SAP AG 2002, Title of Presentation, Speaker Name / 25
Example of a Constant Model
Constant Model Automatic Adaptation of the Alpha factor
-
8/10/2019 Forecasting Calc
26/64
SAP AG 2002, Title of Presentation, Speaker Name / 26
Co sta t ode uto at c daptat o o t e p a acto(12)
The system automatically adjusts the alpha factor based on the iThe system automatically adjusts the alpha factor based on the iThe system automatically adjusts the alpha factor based on the iThe system automatically adjusts the alpha factor based on the initialnitialnitialnitialalpha and the smallest tracking signal.alpha and the smallest tracking signal.alpha and the smallest tracking signal.alpha and the smallest tracking signal.
-
8/10/2019 Forecasting Calc
27/64
Moving Average Formulas
-
8/10/2019 Forecasting Calc
28/64
SAP AG 2002, Title of Presentation, Speaker Name / 28
Moving Average-Formulas
Moving Average-13 Weighted Moving Average-14
No ex-post forecast calculated
Trend Models
-
8/10/2019 Forecasting Calc
29/64
SAP AG 2002, Title of Presentation, Speaker Name / 29
Trend Models
There are four models for data with trend:There are four models for data with trend:There are four models for data with trend:There are four models for data with trend:
Forecast with Trend Model (20)Forecast with Trend Model (20)Forecast with Trend Model (20)Forecast with Trend Model (20)
HoltHoltHoltHolts Method (21)s Method (21)s Method (21)s Method (21)
Second Order Exponential Smoothing (22)Second Order Exponential Smoothing (22)Second Order Exponential Smoothing (22)Second Order Exponential Smoothing (22)
Trend model with Automatic Alpha Adaptation (2nd order) (23)Trend model with Automatic Alpha Adaptation (2nd order) (23)Trend model with Automatic Alpha Adaptation (2nd order) (23)Trend model with Automatic Alpha Adaptation (2nd order) (23)
Same Formula !20 = 21
Holts Method (20 21)
-
8/10/2019 Forecasting Calc
30/64
SAP AG 2002, Title of Presentation, Speaker Name / 30
Holt s Method (20, 21)
Basic ValueBasic ValueBasic ValueBasic Value G(t) = V(t) + (1-) [ G(t-1) + T(t-1) ]
Trend ValueTrend ValueTrend ValueTrend Value T(t) = [(G(t) - G(t-1) ] + (1-)T(t-1)
Forecast value for period (t +1)Forecast value for period (t +1)Forecast value for period (t +1)Forecast value for period (t +1) P(t+i) = G(t) + i * T(t)
Formulas
Second Order Exponential Smoothing (22)
-
8/10/2019 Forecasting Calc
31/64
SAP AG 2002, Title of Presentation, Speaker Name / 31
Second Order Exponential Smoothing (22)
Encompasses a double smoothing method where the basic value ofEncompasses a double smoothing method where the basic value ofEncompasses a double smoothing method where the basic value ofEncompasses a double smoothing method where the basic value ofthe first calculation is used as the input for the second. Thethe first calculation is used as the input for the second. Thethe first calculation is used as the input for the second. Thethe first calculation is used as the input for the second. The result is aresult is aresult is aresult is a
basic value that is more reactive to changes in demand whilebasic value that is more reactive to changes in demand whilebasic value that is more reactive to changes in demand whilebasic value that is more reactive to changes in demand while
minimizing the trend effect.minimizing the trend effect.minimizing the trend effect.minimizing the trend effect.
Trend with Automatic Alpha Adaptation (2nd order) (23)
-
8/10/2019 Forecasting Calc
32/64
SAP AG 2002, Title of Presentation, Speaker Name / 32
Trend with Automatic Alpha Adaptation (2nd order) (23)
This is the same as Second Order Exponential Smoothing except thThis is the same as Second Order Exponential Smoothing except thThis is the same as Second Order Exponential Smoothing except thThis is the same as Second Order Exponential Smoothing except theeeesystems determines the Alpha value. The minimum Alpha is 0.05 ansystems determines the Alpha value. The minimum Alpha is 0.05 ansystems determines the Alpha value. The minimum Alpha is 0.05 ansystems determines the Alpha value. The minimum Alpha is 0.05 andddd
the maximum is 0.90. The system determines the Alpha factor thrthe maximum is 0.90. The system determines the Alpha factor thrthe maximum is 0.90. The system determines the Alpha factor thrthe maximum is 0.90. The system determines the Alpha factor throughoughoughough
an iterative processes of comparing the MAD to the Error Total (an iterative processes of comparing the MAD to the Error Total (an iterative processes of comparing the MAD to the Error Total (an iterative processes of comparing the MAD to the Error Total (ET).ET).ET).ET).
(Same Method as Constant with Automatic Alpha Adaptation).(Same Method as Constant with Automatic Alpha Adaptation).(Same Method as Constant with Automatic Alpha Adaptation).(Same Method as Constant with Automatic Alpha Adaptation).
Trend Dampening Profile
-
8/10/2019 Forecasting Calc
33/64
SAP AG 2002, Title of Presentation, Speaker Name / 33
Trend Dampening Profile
As the historical values do not show a decrease in trend as theAs the historical values do not show a decrease in trend as theAs the historical values do not show a decrease in trend as theAs the historical values do not show a decrease in trend as the marketmarketmarketmarketmatures, a Trend Dampening profile can be used to smooth out thematures, a Trend Dampening profile can be used to smooth out thematures, a Trend Dampening profile can be used to smooth out thematures, a Trend Dampening profile can be used to smooth out the
trend.trend.trend.trend.
Seasonal Models
-
8/10/2019 Forecasting Calc
34/64
SAP AG 2002, Title of Presentation, Speaker Name / 34
Seasonal Models
Seasonal Models are used to depict a Seasonal forecast or a recuSeasonal Models are used to depict a Seasonal forecast or a recuSeasonal Models are used to depict a Seasonal forecast or a recuSeasonal Models are used to depict a Seasonal forecast or a recurringrringrringrringpattern, without any upwards or downwards slope. The pattern ocpattern, without any upwards or downwards slope. The pattern ocpattern, without any upwards or downwards slope. The pattern ocpattern, without any upwards or downwards slope. The pattern occurscurscurscurs
across its season or a number of Seasonal Periods (Usuallyacross its season or a number of Seasonal Periods (Usuallyacross its season or a number of Seasonal Periods (Usuallyacross its season or a number of Seasonal Periods (Usually
recommended to be 12 Months). The trend value and Beta in thisrecommended to be 12 Months). The trend value and Beta in thisrecommended to be 12 Months). The trend value and Beta in thisrecommended to be 12 Months). The trend value and Beta in this
case are zero, signifying no upward or downward slope.case are zero, signifying no upward or downward slope.case are zero, signifying no upward or downward slope.case are zero, signifying no upward or downward slope.
Seasonal Models
-
8/10/2019 Forecasting Calc
35/64
SAP AG 2002, Title of Presentation, Speaker Name / 35
There are three Models associated with the seasonal patterns.There are three Models associated with the seasonal patterns.There are three Models associated with the seasonal patterns.There are three Models associated with the seasonal patterns.
Forecast with the Seasonal Model (30)Forecast with the Seasonal Model (30)Forecast with the Seasonal Model (30)Forecast with the Seasonal Model (30)
Seasonal Trend based on the WinterSeasonal Trend based on the WinterSeasonal Trend based on the WinterSeasonal Trend based on the Winters Method (31)s Method (31)s Method (31)s Method (31)
Season + Linear Regression (35)Season + Linear Regression (35)Season + Linear Regression (35)Season + Linear Regression (35)
Same Formula !30 = 31
Forecast with the Seasonal Model (30)
-
8/10/2019 Forecasting Calc
36/64
SAP AG 2002, Title of Presentation, Speaker Name / 36
( )
This model uses first order exponential smoothing where both AlpThis model uses first order exponential smoothing where both AlpThis model uses first order exponential smoothing where both AlpThis model uses first order exponential smoothing where both Alphahahahaand Gamma are assigned.and Gamma are assigned.and Gamma are assigned.and Gamma are assigned.
Season + Linear Regression (35)
-
8/10/2019 Forecasting Calc
37/64
SAP AG 2002, Title of Presentation, Speaker Name / 37
Seasonal indices calculated
Seasonality removed from data
Forecast created using linear regression
Seasonality added back to forecast
Seasonal Trend Models
-
8/10/2019 Forecasting Calc
38/64
SAP AG 2002, Title of Presentation, Speaker Name / 38
There are two Models for the Seasonal Trend method:There are two Models for the Seasonal Trend method:There are two Models for the Seasonal Trend method:There are two Models for the Seasonal Trend method:
Forecast with Seasonal Trend Model (40)Forecast with Seasonal Trend Model (40)Forecast with Seasonal Trend Model (40)Forecast with Seasonal Trend Model (40)
First Order Exponential Smoothing (41)First Order Exponential Smoothing (41)First Order Exponential Smoothing (41)First Order Exponential Smoothing (41)
Same Formula !40 = 41
Also know as: Holt-Winters Method
And Triple Exponential Smoothing
First Order Exponential Smoothing (40, 41)
-
8/10/2019 Forecasting Calc
39/64
SAP AG 2002, Title of Presentation, Speaker Name / 39
This Model encompasses the same Formula as 20,21,30,31 and usesThis Model encompasses the same Formula as 20,21,30,31 and usesThis Model encompasses the same Formula as 20,21,30,31 and usesThis Model encompasses the same Formula as 20,21,30,31 and usesassigned values for the Alpha, Beta and Gamma Coefficients.assigned values for the Alpha, Beta and Gamma Coefficients.assigned values for the Alpha, Beta and Gamma Coefficients.assigned values for the Alpha, Beta and Gamma Coefficients.
Auto Selection Models
-
8/10/2019 Forecasting Calc
40/64
SAP AG 2002, Title of Presentation, Speaker Name / 40
Auto Selection 1 (50)Auto Selection 1 (50)Auto Selection 1 (50)Auto Selection 1 (50)
Test for Trend and Season (53)Test for Trend and Season (53)Test for Trend and Season (53)Test for Trend and Season (53)
Test for Trend (51)Test for Trend (51)Test for Trend (51)Test for Trend (51)
Test for Season (52)Test for Season (52)Test for Season (52)Test for Season (52)
Seasonal model plus test for Trend (54)Seasonal model plus test for Trend (54)Seasonal model plus test for Trend (54)Seasonal model plus test for Trend (54)
Trend Model plus test for Seasonal Pattern (55)Trend Model plus test for Seasonal Pattern (55)Trend Model plus test for Seasonal Pattern (55)Trend Model plus test for Seasonal Pattern (55)
Auto Model Selection procedure 2 (56)Auto Model Selection procedure 2 (56)Auto Model Selection procedure 2 (56)Auto Model Selection procedure 2 (56)
Same Formula !50 = 53
Auto Selection 1 (50, 53)
-
8/10/2019 Forecasting Calc
41/64
SAP AG 2002, Title of Presentation, Speaker Name / 41
Tests for Both Seasonal and Trend Patterns.Tests for Both Seasonal and Trend Patterns.Tests for Both Seasonal and Trend Patterns.Tests for Both Seasonal and Trend Patterns.Seasonal Test: The Auto Correlation Coefficient is Calculated, tSeasonal Test: The Auto Correlation Coefficient is Calculated, tSeasonal Test: The Auto Correlation Coefficient is Calculated, tSeasonal Test: The Auto Correlation Coefficient is Calculated, thehehehe
Pattern is determined to be Seasonal if the Auto CorrelationPattern is determined to be Seasonal if the Auto CorrelationPattern is determined to be Seasonal if the Auto CorrelationPattern is determined to be Seasonal if the Auto Correlation
Coefficient is Greater than 0.3.Coefficient is Greater than 0.3.Coefficient is Greater than 0.3.Coefficient is Greater than 0.3.
Auto Selection 1 (50, 53)
-
8/10/2019 Forecasting Calc
42/64
SAP AG 2002, Title of Presentation, Speaker Name / 42
A Trend Significance test is carried outA Trend Significance test is carried outA Trend Significance test is carried outA Trend Significance test is carried out
If both are determined to be significant, a Seasonal Trend ModelIf both are determined to be significant, a Seasonal Trend ModelIf both are determined to be significant, a Seasonal Trend ModelIf both are determined to be significant, a Seasonal Trend Model isisisis
used.used.used.used.
If neither tests is determined to be Significant, then the ConstIf neither tests is determined to be Significant, then the ConstIf neither tests is determined to be Significant, then the ConstIf neither tests is determined to be Significant, then the Constantantantant
Model is chosen as a defaultModel is chosen as a defaultModel is chosen as a defaultModel is chosen as a default
Test for Trend (51)
-
8/10/2019 Forecasting Calc
43/64
SAP AG 2002, Title of Presentation, Speaker Name / 43
Used to Test only for Trend.Used to Test only for Trend.Used to Test only for Trend.Used to Test only for Trend.
This follows the Trend Significance test previously defined. IfThis follows the Trend Significance test previously defined. IfThis follows the Trend Significance test previously defined. IfThis follows the Trend Significance test previously defined. If nononono
Significance is found then a Constant Model is Chosen.Significance is found then a Constant Model is Chosen.Significance is found then a Constant Model is Chosen.Significance is found then a Constant Model is Chosen.
Test for Season (52)
-
8/10/2019 Forecasting Calc
44/64
SAP AG 2002, Title of Presentation, Speaker Name / 44
Used to Test only for Seasonal Pattern.Used to Test only for Seasonal Pattern.Used to Test only for Seasonal Pattern.Used to Test only for Seasonal Pattern.
This follows theThis follows theThis follows theThis follows the AutoCorrelationAutoCorrelationAutoCorrelationAutoCorrelation Coefficient Test andCoefficient Test andCoefficient Test andCoefficient Test and choseschoseschoseschoses thethethethe
Seasonal Model if the value is above 0.3. If not a Constant ModSeasonal Model if the value is above 0.3. If not a Constant ModSeasonal Model if the value is above 0.3. If not a Constant ModSeasonal Model if the value is above 0.3. If not a Constant Model isel isel isel is
chosen.chosen.chosen.chosen.
Seasonal model plus test for Trend (54)
-
8/10/2019 Forecasting Calc
45/64
SAP AG 2002, Title of Presentation, Speaker Name / 45
Assumes Seasonal pattern exists and tests for Trend pattern. IfAssumes Seasonal pattern exists and tests for Trend pattern. IfAssumes Seasonal pattern exists and tests for Trend pattern. IfAssumes Seasonal pattern exists and tests for Trend pattern. If aaaa
trend significance is found, then a Seasonal Trend Model is usedtrend significance is found, then a Seasonal Trend Model is usedtrend significance is found, then a Seasonal Trend Model is usedtrend significance is found, then a Seasonal Trend Model is used. If. If. If. If
no significance is found than a Seasonal Model is used.no significance is found than a Seasonal Model is used.no significance is found than a Seasonal Model is used.no significance is found than a Seasonal Model is used.
-
8/10/2019 Forecasting Calc
46/64
Summary of the Automodel 1 selection process
-
8/10/2019 Forecasting Calc
47/64
SAP AG 2002, Title of Presentation, Speaker Name / 47
This shows the Model chosen under the following Conditions:This shows the Model chosen under the following Conditions:This shows the Model chosen under the following Conditions:This shows the Model chosen under the following Conditions:
Automodel If:Trend If: Season Then:Uses Model
40 - Seasonal Trend
20 - Trend
Yes
No
Yes byDefault
55 - Trend Model plus testfor Season
30 - Season
40 - Seasonal Trend
Yes by
Default
No
Yes
54 - Seasonal Model plus
test for Trend
30 - Season
10 - Constant
Yes
No
N/A52 - Test for Season
30 - Trend
10 - Constant
N/AYes
No
51 - Test for Trend
10 - Constant
20 - Trend
30 - Season
40 - Seasonal Trend
No
No
Yes
Yes
No
Yes
No
Yes
50 - Auto Selection 1
or
53 - Test for Trend andSeason
Auto Model Selection procedure 2 (56)
-
8/10/2019 Forecasting Calc
48/64
SAP AG 2002, Title of Presentation, Speaker Name / 48
Tests for Constant, Seasonal and/or Trend models while attemptinTests for Constant, Seasonal and/or Trend models while attemptinTests for Constant, Seasonal and/or Trend models while attemptinTests for Constant, Seasonal and/or Trend models while attempting tog tog tog to
minimize Error by adjusting Alpha, Beta and Gamma..minimize Error by adjusting Alpha, Beta and Gamma..minimize Error by adjusting Alpha, Beta and Gamma..minimize Error by adjusting Alpha, Beta and Gamma..
This model adjusts Alpha, Beta and Gamma between the values of 0This model adjusts Alpha, Beta and Gamma between the values of 0This model adjusts Alpha, Beta and Gamma between the values of 0This model adjusts Alpha, Beta and Gamma between the values of 0.1.1.1.1
to 0.5 in 0.1 increments while calculating the Mean Absolute Devto 0.5 in 0.1 increments while calculating the Mean Absolute Devto 0.5 in 0.1 increments while calculating the Mean Absolute Devto 0.5 in 0.1 increments while calculating the Mean Absolute Deviationiationiationiation
(MAD) for each Iteration. The iteration with the Lowest MAD is(MAD) for each Iteration. The iteration with the Lowest MAD is(MAD) for each Iteration. The iteration with the Lowest MAD is(MAD) for each Iteration. The iteration with the Lowest MAD is thethethetheModel chosen with the appropriate smoothing factors.Model chosen with the appropriate smoothing factors.Model chosen with the appropriate smoothing factors.Model chosen with the appropriate smoothing factors.
Comparision between 50 and 56 (Auto model 1 & 2)
-
8/10/2019 Forecasting Calc
49/64
SAP AG 2002, Title of Presentation, Speaker Name / 49
Auto Selection Model 1 Auto Selection Model 2Auto Selection Model 1 Auto Selection Model 2Auto Selection Model 1 Auto Selection Model 2Auto Selection Model 1 Auto Selection Model 2
Chooses Best Fit of Constant, Trend,Chooses Best Fit of Constant, Trend,Chooses Best Fit of Constant, Trend,Chooses Best Fit of Constant, Trend,
Seasonal, Seasonal Trend.Seasonal, Seasonal Trend.Seasonal, Seasonal Trend.Seasonal, Seasonal Trend.
If no Pattern Detected defaults ConstantIf no Pattern Detected defaults ConstantIf no Pattern Detected defaults ConstantIf no Pattern Detected defaults Constant
ModelModelModelModel
Resource Intensive (NotResource Intensive (NotResource Intensive (NotResource Intensive (Not
recommended for Production use)recommended for Production use)recommended for Production use)recommended for Production use)
Not as precise as Auto Model 2Not as precise as Auto Model 2Not as precise as Auto Model 2Not as precise as Auto Model 2
Determines Best Fit through throughDetermines Best Fit through throughDetermines Best Fit through throughDetermines Best Fit through through
Iterative approach of adjustingIterative approach of adjustingIterative approach of adjustingIterative approach of adjusting
smoothing factors (Alpha, Beta,smoothing factors (Alpha, Beta,smoothing factors (Alpha, Beta,smoothing factors (Alpha, Beta,
Gamma) and determining SmallestGamma) and determining SmallestGamma) and determining SmallestGamma) and determining SmallestMean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)
Determines Seasonal and TrendDetermines Seasonal and TrendDetermines Seasonal and TrendDetermines Seasonal and Trend
Significance through Formulas forSignificance through Formulas forSignificance through Formulas forSignificance through Formulas for
Auto Correlation (SeasonalAuto Correlation (SeasonalAuto Correlation (SeasonalAuto Correlation (Seasonal
Significance) and TrendSignificance) and TrendSignificance) and TrendSignificance) and TrendSignificance TestsSignificance TestsSignificance TestsSignificance Tests
The Croston Model (80)
-
8/10/2019 Forecasting Calc
50/64
SAP AG 2002, Title of Presentation, Speaker Name / 50
The Croston Model (80) is used when demand is sporadic orThe Croston Model (80) is used when demand is sporadic orThe Croston Model (80) is used when demand is sporadic orThe Croston Model (80) is used when demand is sporadic or
intermittent. The return is a Constant model to meet the possibintermittent. The return is a Constant model to meet the possibintermittent. The return is a Constant model to meet the possibintermittent. The return is a Constant model to meet the possiblelelele
sporadic demand.sporadic demand.sporadic demand.sporadic demand.
-
8/10/2019 Forecasting Calc
51/64
Manual Forecast (70)
-
8/10/2019 Forecasting Calc
52/64
SAP AG 2002, Title of Presentation, Speaker Name / 52
The Manual Forecast (70) allows the planner to set their own valThe Manual Forecast (70) allows the planner to set their own valThe Manual Forecast (70) allows the planner to set their own valThe Manual Forecast (70) allows the planner to set their own values toues toues toues to
generate a forecast. The values chosen are all the values thatgenerate a forecast. The values chosen are all the values thatgenerate a forecast. The values chosen are all the values thatgenerate a forecast. The values chosen are all the values that makemakemakemake
up the forecast these are the Smoothing coefficients Alpha, Betup the forecast these are the Smoothing coefficients Alpha, Betup the forecast these are the Smoothing coefficients Alpha, Betup the forecast these are the Smoothing coefficients Alpha, Beta,a,a,a,
Gamma (from the Profile) and the Basic, Trend value and SeasonGamma (from the Profile) and the Basic, Trend value and SeasonGamma (from the Profile) and the Basic, Trend value and SeasonGamma (from the Profile) and the Basic, Trend value and Seasonalalalal
Index. This model should not be used for Background Processing.Index. This model should not be used for Background Processing.Index. This model should not be used for Background Processing.Index. This model should not be used for Background Processing.
No Forecast (98)
-
8/10/2019 Forecasting Calc
53/64
SAP AG 2002, Title of Presentation, Speaker Name / 53
No forecast is conductedNo forecast is conductedNo forecast is conductedNo forecast is conducted
External Forecast (99)
-
8/10/2019 Forecasting Calc
54/64
SAP AG 2002, Title of Presentation, Speaker Name / 54
It is also possible to define your own Forecasting model if theIt is also possible to define your own Forecasting model if theIt is also possible to define your own Forecasting model if theIt is also possible to define your own Forecasting model if the modelmodelmodelmodel
you commonly use is not provided. The external Forecasting featyou commonly use is not provided. The external Forecasting featyou commonly use is not provided. The external Forecasting featyou commonly use is not provided. The external Forecasting featureureureure
allows you to use ABAP to code your own forecasting modelallows you to use ABAP to code your own forecasting modelallows you to use ABAP to code your own forecasting modelallows you to use ABAP to code your own forecasting model.
Trend, Seasonal, Seasonal Trend overview: Formula
-
8/10/2019 Forecasting Calc
55/64
SAP AG 2002, Title of Presentation, Speaker Name / 55
Explanation of the Variables
-
8/10/2019 Forecasting Calc
56/64
SAP AG 2002, Title of Presentation, Speaker Name / 56
333 Univariate Forecast Basics
444 Univariate Models in APOModels in APOModels in APOModels in APO
555 Forecast Error Analysis
Forecast Accuracy Measurements
-
8/10/2019 Forecasting Calc
57/64
SAP AG 2002, Title of Presentation, Speaker Name / 57
Mean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)Mean Absolute Deviation (MAD)
Error Total (ET)Error Total (ET)Error Total (ET)Error Total (ET)
Mean Absolute Percentage Error (MAPE)Mean Absolute Percentage Error (MAPE)Mean Absolute Percentage Error (MAPE)Mean Absolute Percentage Error (MAPE)
Mean Square Error (MSE)Mean Square Error (MSE)Mean Square Error (MSE)Mean Square Error (MSE)
Square Root of the Mean Squared Error (RMSE)Square Root of the Mean Squared Error (RMSE)Square Root of the Mean Squared Error (RMSE)Square Root of the Mean Squared Error (RMSE)
Mean Percentage Error (MPE)Mean Percentage Error (MPE)Mean Percentage Error (MPE)Mean Percentage Error (MPE)
Mean Absolute Deviation (MAD)
-
8/10/2019 Forecasting Calc
58/64
SAP AG 2002, Title of Presentation, Speaker Name / 58
The Mean Absolute Deviation is calculated by the absolute differThe Mean Absolute Deviation is calculated by the absolute differThe Mean Absolute Deviation is calculated by the absolute differThe Mean Absolute Deviation is calculated by the absolute differenceenceenceence
between the exbetween the exbetween the exbetween the ex----post forecast and the actual value.post forecast and the actual value.post forecast and the actual value.post forecast and the actual value.
The Mean Absolute Deviation is the error calculation used toThe Mean Absolute Deviation is the error calculation used toThe Mean Absolute Deviation is the error calculation used toThe Mean Absolute Deviation is the error calculation used to
determine the best fit in the Auto Model 2 Forecasting Model.determine the best fit in the Auto Model 2 Forecasting Model.determine the best fit in the Auto Model 2 Forecasting Model.determine the best fit in the Auto Model 2 Forecasting Model.
Error Total (ET)
-
8/10/2019 Forecasting Calc
59/64
SAP AG 2002, Title of Presentation, Speaker Name / 59
The Error Total is the sum of the difference between the ActualThe Error Total is the sum of the difference between the ActualThe Error Total is the sum of the difference between the ActualThe Error Total is the sum of the difference between the Actual andandandand
the Exthe Exthe Exthe Ex----post forecast.post forecast.post forecast.post forecast.
Mean Square Error (MSE)
-
8/10/2019 Forecasting Calc
60/64
SAP AG 2002, Title of Presentation, Speaker Name / 60
The Mean Square Error is the Average of the sum of the square ofThe Mean Square Error is the Average of the sum of the square ofThe Mean Square Error is the Average of the sum of the square ofThe Mean Square Error is the Average of the sum of the square of
each difference between the exeach difference between the exeach difference between the exeach difference between the ex----post forecast and the Actual value.post forecast and the Actual value.post forecast and the Actual value.post forecast and the Actual value.
Mean Absolute Percentage Error (MAPE)
-
8/10/2019 Forecasting Calc
61/64
SAP AG 2002, Title of Presentation, Speaker Name / 61
The Mean Absolute Percentage Error is the Average Absolute PerceThe Mean Absolute Percentage Error is the Average Absolute PerceThe Mean Absolute Percentage Error is the Average Absolute PerceThe Mean Absolute Percentage Error is the Average Absolute Percentntntnt
Error between the Actual Values and their corresponding ExError between the Actual Values and their corresponding ExError between the Actual Values and their corresponding ExError between the Actual Values and their corresponding Ex----postpostpostpost
Forecast Values.Forecast Values.Forecast Values.Forecast Values.
Root mean Square Error (RMSE)
-
8/10/2019 Forecasting Calc
62/64
SAP AG 2002, Title of Presentation, Speaker Name / 62
The Root Mean Square Error is the Square root of the average ofThe Root Mean Square Error is the Square root of the average ofThe Root Mean Square Error is the Square root of the average ofThe Root Mean Square Error is the Square root of the average of thethethethe
sum of the squared difference between the Actual and Exsum of the squared difference between the Actual and Exsum of the squared difference between the Actual and Exsum of the squared difference between the Actual and Ex----postpostpostpost
Forecast value.Forecast value.Forecast value.Forecast value.
Mean Percentage Error (MPE)Mean Percentage Error (MPE)Mean Percentage Error (MPE)Mean Percentage Error (MPE)
-
8/10/2019 Forecasting Calc
63/64
SAP AG 2002, Title of Presentation, Speaker Name / 63
The Mean Percentage Error is the average percentage error of theThe Mean Percentage Error is the average percentage error of theThe Mean Percentage Error is the average percentage error of theThe Mean Percentage Error is the average percentage error of the
difference between the Exdifference between the Exdifference between the Exdifference between the Ex----post Forecast and the Actual values.post Forecast and the Actual values.post Forecast and the Actual values.post Forecast and the Actual values.
-
8/10/2019 Forecasting Calc
64/64
SAP AG 2002, Title of Presentation, Speaker Name / 64
Thank You