Analytical Engine's Demand planning(DP) mode run comprises of Prepossessing stage, followed by model application & testing stage. In Promotion Effectiveness(PE) mode run of engine, various promotional CFs are prepared and used before Forecast phase starts.
Forecast Phase of Engine Run:
Pre-processing Stage:
1. Treatment of missing values.
2. Detection of intermittency.
3. Preliminary outlier and regime change detection.
4. Removal of obvious (gross) outliers.
5. Data transformation for use in specific models.
Model application & Testing Stage:
1. Checking that the number of data points exceeds at least by two the number of causal factors. This is done to ensure that, No over-fitting occurs and coefficients for all causal factors can be determined.
2. Estimation. Statistical algorithms, are implemented to data and their parameters are calculated.
3. Fit and Residuals calculation. Fit is calculated by applying an estimated model to the historical period. It reflects the ability of the model to reproduce the actual series. The deviation of fit from the actual forms the residual series. The variance of residual, along with complexity (number of estimated parameters) is utilized to compute the weights for model averaging.
4. To check the ability of a model to mimic the actual series, a Fit validation is performed, provided the nableFitValidation flag is on.In Fit validation the residuals undergo a battery of statistical tests.Forecast performs identical calculation to Fit, only for the future period, lead.
5. To perform Forecast validation, both the parameter EnableForecastValidation and the variable ValidFit have to be “True”. This is because if a model reached this stage with invalid fit, it must be running at the highest forecast level, and at this level forecast validation is disabled, allowing a somewhat more liberal treatment of models. In Forecast validation models undergo three tests:
• A test for an unusual zigzag-type jump
more details on Demantra's Engine can be found in Oracle Metalink's Documentation library for Demantra.
4 comments:
Raj
I was looking over for Demantra and came over to your site? Few questions, I appreciate if you answer?
I am SCM Techno Functional and planning to learn Demantra. Does Demantra include any technical work or it is more of a functional work? Is Demantra something, which can be taught on own and I can start looking for a opening. I have no ASCP background at all?
I appreciate if you can answer and I will pick your brain more.
hi vinay,
Demantra has a functional as well as technical side of it. You need to have a mix of knowledge for speedy catching up on Demantra.
You can learn the application on your own too, there are many documents available on Metalink and also published at other sites. ASCP background does help as, Demantra like ASCP is a planning tool and thus one can correlate and learn easily if you know ASCP. But even without ASCP knowledge one can start learning Demantra.
hope this helps.
Raj
Raj
Great to see your reply. Thanks. I was looking all over the net and I think you are the only one who has a blog that talk about Demantra.I read your blog but I couldn't differentiate between Technical and Functional side of Demantra. Can you guide me to a place either on metalink or someplace where I can gather more information on Demantra Technical? Moreover what kind off technical work is involved in Demantra implementation?
Hi Vinay,
You should refer to the implementation guide of Demantra, where you will get all the base data objects list and their usages.
Most of Demantra technical stuff is related to interface building and customization of data pulls ans push for application.
Regards
Raj
Post a Comment