INTERACTIVE IN-MEMORY BASED SALES FORECASTING

• US 20140019207A1
• Filed: 07/11/2012
• Published: 01/16/2014
• Est. Priority Date: 07/11/2012
• Status: Abandoned Application

• Current Assignee: SAP SE
• Original Assignee: SAP AG (SAP SE)
• Inventors: Kraus, Stefan, Pantar, Aravinda, Matthes, Jan, Hoque, S M Fazlul, Wilmer, Guenter, Eichin, Ruediger, Biradarpatil, Kiran
• Application Number:
  US13/546,690
• Publication Number:
  US 20140019207A1
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system and method provide for a sales forecasting application implemented on a user terminal. The sales forecasting system uses integrated predictive and statistical methods to evaluate the reliability of the forecast. The sales forecasting system may perform a statistical analysis to derive a sequence for the influencing attributes, driving sales success in the past, and display the attributes to an end user in a specific sequence. The sales forecasting system may further be implemented through a sequences of stages, including a pipeline analysis stage where the system understands the situation and any possible risks, an analysis stage where the system may analyze past or external influences, and an application stage where the forecasting system applies the insights to a current pipeline and provides a determined simulation.

Claims

1. A method for improving reliability of sales forecasting, the method comprising:

generating a current pipeline based on historical data retrieved from an in-memory database, wherein the in-memory database is primarily stored in Random Access Memory (RAM);

determining a list of influencing attributes based on the current pipeline and retrieved historical data, the influencing attributes being sorted by statistical relevance, wherein the determining the list of influencing attributes is performed by a processor;

displaying the sorted influencing attributes in a user interface of a user terminal, at least one attribute value of the sorted influencing attributes being selectably compared to determine future opportunities;

generating at least one opportunity pipeline, the at least one opportunity pipeline being a function of opportunity data and the influencing attributes, wherein generating the at least one opportunity pipeline includes;

determining a past opportunities portion of the at least one opportunity pipeline based on the historical data,

determining a non-weighted future opportunities portion of the at least one opportunity pipeline based on the historical data, and

determining a weighted future opportunities portion of the at least one opportunity pipeline based on weighted influencing attributes applied to the historical data; and

displaying the at least one opportunity pipeline including at least one of the past opportunities portion, the non-weighted future opportunities portion, and the weighted future opportunities portion.

2. The method according to claim 1, further comprising:

generating a list of attribute values from a selected influencing attribute.

3. The method according to claim 1, further comprising:

displaying the current pipeline over a designated time period, the designated time period being one of a month, a sales quarter, multiple sales quarters, or a year.

4. The method according to claim 1, wherein the opportunity data is stored in the in-memory database.

5. The method according to claim 1, wherein some of the influencing attributes are calculated instantaneously after the historical data is retrieved from the in-memory database.

6. The method according to claim 1, wherein the opportunity pipeline includes an expected value opportunity.

7. The method according to claim 1, wherein the opportunity pipeline includes a weighted opportunity.

8. The method according to claim 1, further comprising:

extracting the historical and opportunity data from a plurality of subsystems and loading the extracted data into the in-memory database.

9. The method according to claim 2, further comprising:

upon a user selection of the at least one attribute value from the list of attribute values, displaying at least one generated graphical display comparing the at least one attribute value to another selected attribute value.

20. The method according to claim 1, wherein some of the influencing attributes are calculated instantaneously after the previous sales orders are retrieved from the in-memory database.

10. A forecasting system for providing interactive sales forecasts, the system comprising:

at least one user terminal displaying a user interface, the sales forecasting system displayed on the user interface;

an in-memory database storing historical data and opportunity data, wherein the in-memory database is primarily stored in Random Access Memory (RAM); and

a processor operable to;

retrieve the historical data from the in-memory database;

generate a current pipeline based on the retrieved historical data;

determine a list of influencing attributes based on the current pipeline and retrieved historical data, the influencing attributes being sorted by statistical relevance;

display the sorted influencing attributes in a user interface of a user terminal, at least one attribute value of the sorted influencing attributes being selectably compared to determine future opportunities; and

generate at least one opportunity pipeline, the at least one opportunity pipeline being a function of opportunity data and the influencing attributes, wherein to generate the at least one opportunity pipeline, the processor is further configured to;

determine a past opportunities portion of the at least one opportunity pipeline based on the historical data,

determine a non-weighted future opportunities portion of the at least one opportunity pipeline based on the historical data, and

determine a weighted future opportunities portion of the at least one opportunity pipeline based on weighted influencing attributes applied to the historical data; and

display the at least one opportunity pipeline including at least one of the past opportunities portion, the non-weighted future opportunities portion, and the weighted future opportunities portion.

11. The system according to claim 10, further comprising:

an advanced business application programming (ABAP) system to access the stored historical and opportunity data from the in-memory database.

12. The system according to claim 10, wherein the sales forecasting system is implemented on an integrated business platform.

13. The system according to claim 10, wherein a list of attribute values is generated from a selected influencing attribute.

14. The system according to claim 10, wherein the current pipeline is displayed over a designated time period, the designated time period being one of a month, a sales quarter, multiple sales quarters, or a year.

15. The system according to claim 10, wherein some of the influencing attributes are calculated instantaneously after the historical data is retrieved from the in-memory database.

16. The system according to claim 10, wherein the historical and opportunity data is extracted from a plurality of subsystems and loading the extracted data into the in-memory database.

17. The system according to claim 10, wherein upon a user selection of the at least one attribute value from the list of attribute values, at least one generated graphical display is displayed comparing the at least one attribute value to another selected attribute value.

18. (canceled)

19. A method for providing sales forecasts based on sales opportunities data and previous sales orders, the method comprising:

extracting the previous sales orders and sales opportunities data from a plurality of subsystems;

loading the extracted data into the in-memory database;

generating a current pipeline based on the previous sales orders;

determining a list of influencing attributes based on the current pipeline and the previous sales orders;

sorting the influencing attributes by a statistical relevance;

generating a list of attribute values from a selected influencing attribute;

selectably comparing at least one of attribute value of the selected influencing attribute;

displaying the compared attribute values in at least one graphical representation in a user interface of a user terminal to determine future opportunities; and

generating at least one opportunity pipeline that is displayed in the user interface, the at least one opportunity pipeline being a function of opportunity data and the influencing attributes and being displayed in the user interface over a designated time period.

21. A non-transitory computer-readable medium embodied with computer-executable instructions for causing a computer to execute instructions, the computer instructions comprising:

generating a current pipeline based on historical data retrieved from an in-memory database, wherein the in-memory database is primarily stored in Random Access Memory (RAM);

determining a list of influencing attributes based on the current pipeline and retrieved historical data, the influencing attributes being sorted by statistical relevance, wherein the determining the list of influencing attributes is performed by a processor;

displaying the sorted influencing attributes in a user interface of a user terminal, at least one attribute value of the sorted influencing attributes being selectably compared to determine future opportunities;

generating at least one opportunity pipeline, the at least one opportunity pipeline being a function of opportunity data and the influencing attributes, wherein generating the at least one opportunity pipeline includes;

determining a past opportunities portion of the at least one opportunity pipeline based on the historical data,

determining a non-weighted future opportunities portion of the at least one opportunity pipeline based on the historical data, and

determining a weighted future opportunities portion of the at least one opportunity pipeline based on weighted influencing attributes applied to the historical data; and

displaying the at least one opportunity pipeline including at least one of the past opportunities portion, the non-weighted future opportunities portion, and the weighted future opportunities portion.