Oracle Mix Open World Session

Vote for this session @ Oracle Mix

Integrated Collaborative Forecasting for CPG Industry

Abstract

This session will explore how an integrated collaborative platform can be build using Value Chain Planning modules to enable usage of POS, Withdrawals, Shipments, Bookings and Trade promotions in building an integrated collaborative forecast using Demantra.

This session will also discuss:
1. S&OP solution options
2. Challenges faced during implementation
3. CPG Success Stories

Vote for this session @ Oracle Mix.

Integrated Causal Exponential Model (BWint)

Demantra has Integrated Causal Exponential Model (BWint) as one of the models available for analytical engine. This also is a regression model, known as Multiplicative regression - winter model. The model works only in DP mode. It runs multiplicative regression on Causal data (short CFs) and then smooths out the residual series exponentially like HOLT.

Data Type: Good fit for capturing Trends, Seasonality and Causality in demand data.

Example: Here is an example of where forecast is generated by Bwint model of Demantra. Look at how engine is able to capture seasonality and demand trend accurately, providing a good baseline forecast for planners to start with.

Demantra 7.3.1: Fast Divider Engine parameters

Just a small note for those who wish to be on are on 7.3.1 level.

If you have noticed or are using engine parameters "RunFastDivider" & "RunPartialDivider" in your Demantra 7.3.0.1 install, there is a change awaiting you in 7.3.1 release. While the concept of fast divider which came with 7.3 release to speed up the engine run remains in existence, these parameters no more exist. This was established that these parameters need not exist to support fast divider process, hence Oracle decided to take out these parameters from 7.3.1 release.

Basics of Demand Forecasting

CHAPTER 5- DEMAND FORECASTING

View more presentations from Bobtb

Few Forecasting Phrases

Forecasting in business is like sex in society, we have to have it, we cannot

get along without it, everyone is doing it, one way or another, but nobody is

sure he is doing it the best way.

-G W Plossl

Last Frontiers for Profits

Forecasting is like trying to drive a car

blindfolded and following directions

given by a person who is looking

out of the back window

- unknown

All forecasts are wrong

Those who claim to forecast the future

are all lying even if, by chance,

they are later proved right .

Demantra 7.3.1 released

Few key features which 7.3.1 has to offer are:

• Support for Service Parts Forecasting: Seeded integration now available between Demantra and Service Parts Planning(SPP) module. For customers implementing SPP module this integration can help them use Demantra for developing a more accurate Service(Spare) Parts forecast.
• Support for Multiple Business Processes: Forecast tree and Causal Factors can now be setup differently for each engine profile, allowing better flexibility around setting up analytical engine for different business processes.
• Enhanced Proport: Improved Proport process performance by providing additional parameters to control proport run.
• Worksheet Performance improvement: Additional parameters to create parallel hints for specific worksheets which can help in improving the performance of Demantra worksheets.
  
• Support for Rolling Data Profile Groups: Users can now assign rolling data profiles to a group and then can call these groups for execution using workflow. This feature increases flexibility around archiving process within Demantra.

New versions of various Demantra documentation now available in Oracle MySupport @

Oracle Demantra Documentation Library [ID 443969.1]

Demantra 7.3: Engine split based on series

Whas is NEW ?:
Demantra 7.3 has come up with quite few features which customers have been wishing to see. One of these is ability to split statistical forecast which generated at aggregated level to split down to lowest level based on user defined/controlled proportions. Prior to 7.3 this split was always based on historical proportions and there was no workaround for it. These historical proportions were calculated based on every product and location combinations historical monthly sales averages using proport procedure. Split by series option allows user to pick a series which dictates weights for dis-aggregation of baseline forecast.

How we USE it?
1. Define a new series with server expression, the server expression gets used in weight calculation.
2. Using Business modeler setup parameter: ENGINE > PROPORT tab > parameter name "ProportionSeries" shall be populated with the internal name of the above series.
3. Select combinations/population to use SPLIT MECHANISM by using series "Engine Proportion Method" in a worksheet. The series has two dropdown values, Matrix Based Proportions which is the default and Series Based Proportions which is the value required for series based split.

Oracle Open World 2010: Sales and Operations Planning for the Food and Beverage Industry

Join us at Oracle Open World 2010 for a session on "Sales and Operations Planning for the Food and Beverage Industry"

http://www.eventreg.com/cc250/sessionDetail.jsp?SID=315911