Auto Model 2 - Constant forecast 1 historical period

I have a composite forecast (100% each) consisting of 5 univariate models that should select the best model based on MAD. I have a product that has only 1 historical period of actuals in the last 36 months. I would have expected the Auto Model 2 to forecast "zero" but it has recommended a constant forecast of the same value as the 1 historical period for the next 24 months.
Is there a parameter that should be modified in order to improve the forecast. Any help on optimizing the parameters would also be very helpful. I have yet to hear of a great success story with Auto Model 2.
Thank you.

Hi,
You need at least 3 historical periods and 2 seasonal cycles (if valid) to initiate the model. Since the model is not initialized, the procedure used copy history model i.e. historical data used as forecast data for the entire forecast horizon.
Thanks,
Rajesh

Similar Messages

Forecasting using historical values

I am doing forecasting for a material. I have created the forecasting view for the material and entered the consulption values. I want the forecasting output to create a forecast where the current month' s forecast = the same month's historical sales last year. When I try to execute the forecast the 'forecast execution' tab has the 'historical' as greyed out. Is there a way I can copy historical values as forecast.
thanks

Hi John,
As per my understanding you want that that the sales for month jan-2008 = forecast for jan-2009.
If that is the requirement then you can maintain the following setting.
Model = D constant
Period indicator = M
histroy period = 12
Forecast period = 12
Maintain the Consumption for the whole year 2007.
Regrads
Kaushik

Forecasting: all historical values are zero

Hello,
I would like to execute forecast for a specific material.
Then I'm in MM02 in forecasting view, I filled all necessary parameters and I press "execute forecasts".
I received different pop ups, and one is "Between 11.2006 and 10.2011 all historical values are zero".
If I go out of this, and press on "Consumption vals", I have no data for unplanned consumption but if I click on "Total consumption", I got all values for each period of my historical periods.
So why do I have this message that historical values are zero? Then I have no chance to execute forecast with that behavior.
Same with several other materials.
Thanks for help.

Dear Olivia,
In MM of forecasting view there is filed Hist. periods which you could have probably maintain more than 12 months say 60. So starting from current months it will go backward & search value for last 60 months. In your case it is not finding any past values. Have you maintain it in Additional data of material master Consumption tab ? Maintain some values for months & then try
Regards
Abhijit Gautam

I need to load for a historical period for sales order ? how to load it?

Hi all,
I need to load the data for the historical period. Say 012.2008 month data. I have deleted the set up tables and trying to reload the setup tables.
but i can find the calendar year, month nor fiscal period.
i can see only sales document number along witht the company code.
How to identify the sales document number for 012.2008 from r/3 and run the setup tables.
Pls help me on this!!
Thanks
Pooja

Hi,
You are trying to do a historical load for 2LIS_11? In that case, check the VBAK/VBAP table, and find the document ranges based on the posting date. VBAK will give you the ranges, while putting the same range in VBAP wll give you the number of item documents that would be loaded. You would be able to split the doc ranges in that case for doing parallel setups.
Alternatively if the data volume is low, do a full setup and then put the selections in the info package itself.
Regards.

How to determine the values for Model Parameters in Forecasting

Hello Gurus,
On basis we will determine the values for the Model Parameter values (Alpha, Beta, Gamma, Sigma).
Thanks,
Siva.

Dear Siva,
the values are dependent from the forecast stratey and forecast model.
The forecast strategy determines the method or the techniques that are used to create the forecast. You set the forecast strategy in the forecast profile.
There are some settings that you must make for certain forecast strategies. The table below shows you which settings these are. You make these settings either in the univariate forecast profile or under the Model and Parameters tabs of the Forecast view on the demand planning desktop.
Model initialization is the process by which the system determines the necessary model parameters for the chosen forecast model. These parameters are in following link:
http://help.sap.com/saphelp_scm50/helpdata/en/ac/216b74337b11d398290000e8a49608/frameset.htm
I hope this helps you further.
Regards,
Tibor

Run Forecast for previuse period

We have certain materials with MRP type VM and want to run forecast first The Period Indicator is M (month).
When user press the run Forecast button, a pop up screen periods appears and you should select a current period 8.2007 or next 9.2007 to run a forecast but for testing AND Due to business requirements, we upload consumption and open PO till 31-5 so we need to run forecast for 6.2007 period to compare values with legacy system before going life.

Hello Chintamani,
Why you want to post the depreciation for future period?
Is the future fiscal year in open or is the posting period open for that? If no, please open that period with AJRW T code if you want to post the depreciation for future period but it is not recommendable.
Check the posting period once again because the given posting period belongs to future year? So please do re-chk and give correct period according to your current fiscal year.
You can get your fiscal year details and assignment of fiscal year variant to the co,code details in OB29 and OB37 t codes respectfully.
Check the OSS Note: 1150235 - Preventing depreciation posting run for future
I hope it helps else revert us with your query.
Thanks & Regards,
Lakshmi S

How to lock historical periods and want to open current month to write

we are having Aso cube, and we need to lock historical periods and need to open the current month for the users for write. and also need to lock scenario. can any one suggest me how to do this?

JohnGoodwin wrote:
Madhvaneni wrote:
Hi,
You will not be able to write back on ASO cube, it's possible only on BSO cube, you can user filters on BSO cube to restrict access on previous months.
thanks
sriYes you can, you can write to level 0 members (From 9.3.1 I think)
Cheers
John
http://john-goodwin.blogspot.com/
I thought so too, but I have not managed to get it to work. I was only playing around with "new features" (as we recently upgraded to 9.3.1.) nothing that required production intensive research.

Forecast model K (Constant with smoothing factor adjustment)

Hi All,
i am using forecast model K in materail master. I would like to know the system calculation on forecast value?
For Example:
Consumption qty maintained in material master for last 3 months.
Period          Total consumption
04.2011     100
03.2011     150
02.2011     200
When i am using Forecast model K, system is calculating as follows,
Period       Orig. HV   Corr. HV   Ex-post FV     Orig. FV
M 02.2011          200        200
M 03.2011          150        150        200
M 04.2011          100        100        155
M 05.2011                                                           106
05.2011     Forecast value is 106, Basic value is 105.500, Error total is -105 and MAD is 27.
I would like to know the system calculation of these value. Particularly Basic value and MAD.
And also the difference between Forcast Model D and K if possible.
When i am using Forecast model D, system is calculating as follows,
Period       Orig. HV   Corr. HV   Ex-post FV Orig. FV
M 02.2011          200        200
M 03.2011          150        150        200
M 04.2011          100        100        190
M 05.2011                                           172
Basic value 172.000,         MAD 38,         Error total -140
Thanks in advance,
Babu

MODEL K:
Constant Model with First-Order Exponential Smoothing
The constant model with first-order exponential smoothing is derived as in formula (5). A simple transformation gives the basic formula for exponential smoothing as shown in (6).
To determine the basic value, you only require the basic value from the preceding period, the last past consumption value and the alpha smoothing factor. The smoothing factor weights the most recent consumption values more than the less recent ones, so that they have a stronger influence on the forecast.
The forecast value is the basic value for the last period for which historical data is avaialble, that is the last ex-post period.
where k> n
How quickly the forecast reacts to a change in consumption pattern depends on what value you give the smoothing factor. If you set alpha to be 0, the new average is equal to the old one and the basic value calculated previously remains; that is, the forecast does not react to current consumption data. If you give alpha the value 1, the new average equals the last consumption value.
The most common values for alpha lie between 0.1 and 0.5. An alpha value of 0.5 weights past consumption values as follows:
1st historical value : 50%
2nd historical value : 25%
3rd historical value : 12.5%
4th historical value : 6.25%
and so on.
The weightings of past consumption data can be changed by one single parameter. Therefore, it is relatively easy to respond to changes in the time series.
The constant model of first-order exponential smoothing derived above is applicable to time series that do not have trend-like patterns or seasonal-like variations.
MODEL D:
I think that simple constant model is just a normal average.

Forecasting Error messages : CBP with auto model selection

Hi
I need to understand forecasting errors. Im working on consumption based planning with MRP type 'V2', when i execute the forecast i get error messages as"timeseries characteristics changed", "parameter optimization accesssed", "expost forecast carried out" etc. I checked in the customization where the errors are assigned to error classes(class 1 to 8). Can someone tell me how to interpret these errors, if possible any documentation reg this errors would be useful. "[email protected]"
Regards
Sam
Message was edited by:
sam litecky

Hi
My requirement is to calculate reorder point and safety stock via past consumption, so thats why im using MRP type V2. Pls correct me if this mrp type is wrong for calculating safety stock and reorder point based on past consumption or to use any other mrp type. any documentation on forecast error messages would be really great with points assured."[email protected]"
Regards
Sam
Message was edited by:
sam litecky

Implementation of state space model with constant disturbance in mathscript and simulation

I am new to LabVIEW and now I am doing a project realizing heater control in 8 rooms.
I have realized the state space model in the form x(k+1)=x(k)+u(k) using mathscript (using c_to_d) and feed it into control and simulation loop for simulation.
My problem is, in my project, I have to consider the disturbance from the other rooms. So the statespace model changed to be x(k+1)=x(k)+u(k)+E*d, where E is the matrix concerning the disturbance and d is the vector of disturbance. How could I implement the disturbance and discretize the new model in mathscript and which function to choose for the simulation. Discrete state space stochastic model?
Appreciate your kind help.

Hello, state space models in LabVIEW most of the time are being implemented by utilizing mathscript syntax
in addition with some functions of the LabVIEW Control Design and Simulation Module.
There´s a couple of nice tutorials for control design with these tools which I´d like to point you to as a first step.
http://www.ni.com/white-paper/6368/en/
http://www.ni.com/white-paper/6368/en/
http://www.ni.com/white-paper/6435/en/
http://home.hit.no/~hansha/documents/lab/Lab%20Work/MathScript/MathScript%20Lab%20-%20Part%20II.pdf
regards
Marco Brauner AES NIG

Rpd Modelling, Report design - Forecast Measure

Hi,
I have a reporting requirement to compare the forecast measures across months:
The report format is such: Dashboard Prompt => 'Month' Selection... say M1
If month not selected in the prompt then take the current month, say M1
Revenue
Month - 3 months 120
Month - 2 months 110
Month - 1 month 100
Taking M1 = Aug in above scenario:
Revenue
May 120
June 110
July 100
How should i show the previous months data in my report given a value for a month? In this case previous 1month, 2 month and 3 month.
Thanks

Hi,
Thanks for the reply. But I am not able to achieve this scenario with pivot table. Maybe you can explain how to achieve it with pivot table or some other approach. I will explain again:
Prompt: Month= M1
Forecast Revenue
M1 -1month
M1 -2months
M1- 3months
Say M1 = Aug
Forecast Revenue
July
June
May
Thanks

Set auto shut down for iPod touch after period of inactivity

I keep falling asleep with my iPod on. My old MP3 player had a setting where it automatically shutdown after a specified period of inactivity. Is there a download or setting of some sort that will make the ipod touch do the same?

I can't try it out for you now and don't know if it's on 2.x, but read p. 32 of the IPT manual under Sleep Timer. The option is under the Clock -> Timer on the Home menu. If the feature is still there...
Here's a link to the online manual:
[http://manuals.info.apple.com/en/iPodtouch_FeaturesGuide.pdf]

Forecast model selection

hi.
can anyone pls explain me how the fcst models are selected during DP implementation. especially when we have ovet 1000 products and when users have no knowledge abt forecasting.
thanks

5,
During auto model selection, each forecasted object is first initialized, then analyzed, then forecasted, individually.
at this moment i'm not interested in automodel selection
No problem; just pick one of the simplest models, such as 'Constant' or 'Trend'. You already said that the client's users are not familiar with forecasting, so they don't really have any business requirement to fill; they won't care as long as they get a forecast.
I recommend that you not lose a lot of sleep on this issue. This is not like other implementations you may have done, where the results must strictly meet certain business rules. In the end, the output is just a forecast, a prediction of the future. The forecast will be wrong no matter what you do, since humans cannot predict the future. At least the ones that I know cannot......
Best Regards,
DB49

Apply custom GUID forecast profile to reforecasting activity?

Hi APO Experts,
My company currently uses only one master forecast method (auto model selection 2, forecast method 56) for every individual customer that we have in APO (~10,000 customers.) I would like to fine tune the process and be able to specify a forecast for certain individual accounts. We use SAP APO version 3.1.
In interactive forecasting mode, I have found the option to "Save assignment with unique forecast profile" (under Settings -> Forecast Profile) and I am now able to create customer specific forecasts with a unique "GUID." However, I am not sure how to utilize these forecasts through a roll forward. I roll my customer forecast window forward every month (ie, i change it from April 2011 - April 2012 to May 2011 - May 2012) by running a Mass Processing activity. But I can not find the GUID forecast profiles when I set up the mass processing activity. I tried deactivating the "always use job profile" button but that still doesn't work - instead of using the GUID specific forecast profiles during the reforecasting, APO will populate those customers with the default master forecast profile. Is there a step that I am missing?
I appreciate your time and help,
-- K

Hi arun,
If i understand your situation,
You put
Validity start date as may and validity end date as dec
constant factor before start date '0'
constant factor after end date '100'
still you see forecast for march april.
if that is the issue, This might happen as per default settings, i think the default settings are constant factor before start date as 100%.
do the following
I dont know how the screens look in 4.1
But in the phase in profiles go to Menu option GOTO> settings
there you can define if constant factor by default should be zero or hundred.
The main reason why this happens is if you try to put 0 as the constant factor before the start date, it does not save anything. so you need to make the default settings that constant factor before the start date is 0 %.
let me know if this helps you or if the problem still persists.
Thanks,
Mythilee

Need help with seasonal forecast model

I am really struggling to get accurate forecast results for CBP using the seasonal forecast model. Our business has relatively constant consumption for 9 months of the year, say an average of 200,000 quantity per month. Then as we enter the 'holiday the season', there is a rapid increase in consumption to as much as 1.6 million per month in December.
Seasonal model seems to work fine if my period indicator is monthly. But our consumption period and forecast needs to be daily. We have enough history going back to January 2010. Can somebody suggest what forecast view settings I should be trying? ... historical periods, intialization periods, periods per season, etc??
I just can't seem to get the same forecasted holiday spikes for 2011 holiday season (Oct - Dec) or 2012.
Thanks, Vlad

Hi B.
to expose an Adaptive RFC model to other DCs you must explicitly add the following entities to the public part of your DC:
- Adaptive RFC Model entitiy
- Logical Dictionary
The Public Part Purpose must be defined as "Compilation".
Important: To expose the Public Part to another DC you must explicitly trigger a DC Build (context menu item 'Development Component -> Build ...', so that the Public Part Archives is being generated. Without an existing PP archive the Client DC cannot 'see' the exposed Public Part Entities of the Service DC.
Regards, Bertram

Auto Model 2 - Constant forecast 1 historical period

Similar Messages

Maybe you are looking for