PREDICTIVE AND PROFILE LEARNING SALES AUTOMATION ANALYTICS SYSTEM AND METHOD

• US 20080162487A1
• Filed: 12/28/2006
• Published: 07/03/2008
• Est. Priority Date: 12/28/2006
• Status: Active Grant

• Current Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Original Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Inventors: Richter, James Neal
• Granted Patent: US 8,527,324 B2
• Time in Patent Office: Days
• US Class Current: 707/10
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 10/06395 Quality analysis or management
• CPC Class Codes: G06Q 10/06398 Performance of employee with respect to a job function
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

A sales automation system and method, namely a system and method for scoring sales representative performance and forecasting future sales representative performance. These scoring and forecasting techniques can apply to a sales representative monitoring his own performance, comparing himself to others within the organization (or even between organizations using methods described in application), contemplating which job duties are falling behind and which are ahead of schedule, and numerous other related activities. Similarly, with the sales representative providing a full set of performance data, the system is in a position to aid a sales manager identify which sales representatives are behind others and why, as well as help with resource planning should requirements, such as quotas or staffing, change.

Claims

1. A sales automation system comprising:

a central data repository including time stamped cached and sales records, idealized and learned sales data and performance metrics;

a repository of raw sales records including raw sales data; and

a machine learning and forecasting module functionally communicable with said central data repository and said repository of sales records and functionally operable to retrieve data from said central repository and said repository of raw sales records and where said machine learning and forecasting module has functional data manipulation components operable to produce metric scores, derived sales data learned sales data and store said data in the central data repository.

2. The sales automation system as recited in claim 1, further comprising:

a data query module having functional algorithms to receive a user initiated query and query based on the user initiated query the central data repository to transmit to said query module the cached sales records, idealized and learned sales data, and performance metrics; and

said data query module having run-time functional algorithms operable to apply transforms, idealized and learned functions and data models to the transmitted data.

3. The sales automation system as recited in claim 2, where said data manipulation components includes a data manipulation algorithm, a data mining and forecasting algorithm, and a pre and post data mining heuristics engine.

4. A sales automation system comprising:

a central data repository included time stamped cached sales records, idealized and learned sales data, and performance metrics;

a repository of raw sales records including raw sales related data; and

a future planning and analysis module functionally communicable with said central data repository and said repository of raw sales records and functionally operable to retrieve data from said central repository and said repository of raw sales records and where said future planning and analysis module has functional analysis components operable to solve for variable based on an input scenario.

5. The sales automation system as recited in claim 4 further comprising:

a machine learning and forecasting module functionally communicable with said central data repository and said repository of sales records and functionally operable to retrieve data from said central repository and said repository of raw sales records and where said machine learning a forecasting module has functional components operable to produce derived sales data outputs.

6. The sales automation system as recited in claim 5 further comprising:

a data query module having functional algorithms to receive a user initiated query and produce conditional data and query the central data repository and said machine learning and forecasting module to transmit derived sales data to the date query module and produce analysis outputs loosed on conditional data; and

where said future planning and analysis module creates an input scenario based on the conditional data, derived sales data and analysis outputs and save for the variable using a scenario analysis engine.

7. A sales automation method comprising:

providing a central repository of ideal and learned sales data profiles and a repository of raw sales data;

extracting raw sales data from the repository of raw sales data and extracting ideal and learned sales data profiles from the central repository;

learning a central sales data pattern based on a forecasting formulation of raw historical sales models based on raw sales data and learning a new sales data profile based on a formulation of learned sales models based on ideal and learned data profiles;

storing the new sales data profiles and central sales data patterns to the central repository scoring performance of central sales data patterns based on new sales data profiles.

8. The sales automation method as recited in claim 7 further:

extracting heuristics from the central repository for learning the new sales data profile and central sales data patterns.

9. The sales automation method as recited in claim 8 where scoring performance includes assigning a quality score based on comparative grading relative to new sales data profiles based on learned data profiles and assigning an absolute grading relative to new sales data profiles based on ideal sales data.

10. A sales automation method comprising:

providing a central data repository having time stamped cached sales records, idealized and learned sales data, and performance metrics and further providing a repository of raw sales records including raw sales related data;

deriving sales data forecasts for a sales metric utilizing a machine learning and forecasting module based on idealized and learned and raw sales data;

defining a desired sales goal relative to the forecasted sales metric and defining an input scenario based on the desired sales goal; and

deriving alterations to sales parameters required to achieve the desire sales goal.

11. The sales automation method is recited in claim 10, where deriving the sales data forecasts for a sales metric includes forecasting based on user input manipulations.

12. The sales automation method as recited in claim 11 further comprising:

displaying to a user the alterations to the sales parameters need to meet the desired sales goal.

13. The sales automation method as recited in claim 12, further comprising:

deriving alterations to the quantity of individual data generation sources to achieve the desired goal.

14. A sales automation method comprising:

providing a repository of ideal and learned sales data

profiles and a repository of raw sales data;

extracting raw sales data and extracting ideal and learned sales data;

defining a sales pipeline having a construct of a series of stages thereby defining a sales strategy where each stage is assigned a conversion rate and assumed value potential;

correlating the raw sales data among the series of stages based on the respective task;

correlating the ideal and learned data among the series of stages based on respective task;

developing a predictive model of a conversion rate of the sales strategy base on the correlating of the ideal and learned data; and

applying the predictive model to the correlated raw sales data and developing a raw predictive model to a row conversion rate.

15. A method comprising:

determining at least one first revenue forecasting parameter based on at least one performance characteristic of at least one person supporting generation of revenue for the organization; and

determining at least one second revenue forecasting parameter to forecast the revenue of an organization, wherein the at least second forecasting parameter is determined at least in part from sales opportunities in a sales pipeline; and

forecasting revenue of the organization using at least in part the first and second forecasting parameters.

18. The method according to claim 15 further including maintaining a profile for at least one of the persons, wherein the profile includes at least one parameter indicative of the capability to generate revenue.

16. The method according to claim 16 further wherein the at least one performance characteristic is based on historical performance of the person.

17. The method according to claim 16 further wherein the performance characteristic is based on the classification of the person'"'"'s capability to generate revenue for the organization.

19. A method comprising:

comparing a learned profile of a sales person or sales group against at least one other reference profile; and

generating at least one report indicating the results of the comparison, wherein the report breaks down areas of difference between the is adapted to assist in predicting the success of the sales person or sales group to achieve a sales goal.

20. A method according to claim 19 further including using the results of the comparison to project revenue for the sales person or sales group.

21. A method according to claim 20 further including generating at least one score indicating the deviance between the projected revenue and a revenue goal.

22. A method according to claim 19 further wherein the reference profile is a known-good profile or an ideal profile.

23. A method comprising:

using real sales data to build a learned model of a strategy-pipeline;

comparing the learned model to an ideal model of the strategy-pipeline; and

using results of the comparison to predict pipeline throughput for at least one person or group of persons.

24. A method according to claim 23 further including generating at least one score for the at least one person or group that indicates a deviation from the ideal model.

25. A method comprising determining the likelihood of meeting a revenue goal using a learned profile of an individual or group.

26. A method according to claim 25 further including reallocating sales quotas for the individuals or groups based on the likelihood of meeting the revenue goal.

27. A method according to claim 25 further including reallocating sales territories for the individuals or groups based on the likelihood of meeting the revenue goal.

28. A method comprising:

using a learned profile of an individual or group of individuals to determine the effect on future revenue of an organization resulting from at least one change in the individual or group of individuals, wherein the at least one change is selected from the group;

adding additional individuals to the group of individuals, replacing one individual for another individual, or eliminating an individual.

29. A system comprising:

a storage device adapted to store one or more performance characteristics of one or more revenue-generating personnel of an organization;

a processing device communicatively coupled to the storage device and adapted to;

determine at least one first revenue forecasting parameter based on at least one performance characteristic of at least one person supporting generation of revenue for the organization;

store the at least one first revenue forecasting parameter in the storage device;

determine at least one second revenue forecasting parameter to forecast the revenue of an organization, wherein the at least second forecasting parameter is determined at least in part from sales opportunities in a sales pipeline;

store the at least one second forecasting parameter in the storage device;

access the at least one first and at least one second parameters; and

forecast revenue of the organization using at least in part the first and second forecasting parameters.

30. A system according to claim 29 wherein the at least one performance characteristic uses historical performance of the person.

31. A system according to claim 29 wherein the at least one performance characteristic uses the classification of the person'"'"'s capability to generate revenue for the organization.

32. The system according to claim 29 wherein the processing device is further adapted to:

maintain a profile for the at least one person, wherein the profile includes at least one parameter indicative of the capability to generate revenue.

33. A system comprising:

a storage device adapted to store one or more profiles of one or more sales people, one or more profiles of one or more sales groups, and one or more reference profiles;

a processing device communicatively coupled to the storage device and adapted to;

compare a learned profile of a sales person or sales group against at least one other reference profile; and

generate at least one report indicating the results of the comparison, wherein the report breaks down areas of difference between the is adapted to assist in predicting the success of the sales person or sales group to achieve a sales goal.

34. A system according to claim 33 wherein the processing device is further adapted to use the results of the comparison to project revenue for the sales person or sales group.

35. A system according to claim 34 wherein the processing device is further adapted to generate at least one score indicated the deviance between the projected revenue and a revenue goal.

36. A system according to claim 34 wherein the reference profile is a known-good profile or an ideal profile.

37. A system comprising:

a storage device adapted to store real sales data;

a processing device communicatively coupled to the storage device and adapted to;

use the real sales data to build a learned model of a strategy-pipeline;

compare the learned model to an ideal model of the strategy-pipeline; and

use results of the comparison to predict pipeline throughput for at least one person or group of persons.

38. A system according to claim 37 wherein the processing device is further adapted to generate at least one score for the at least one person or group that indicates a deviation from the ideal model.

39. A system comprising:

a processing device adapted to;

determine the likelihood of meeting a revenue goal using a learned profile of an individual or group.

40. A system according to claim 39 wherein the processing device is further adapted to reallocate sales quotas for the individuals or groups based on the likelihood of meeting the revenue goal.

41. A system according to claim 39 wherein the processing device is further adapted to reallocate sales territories for the individuals or groups based on the likelihood of meeting the revenue goal.

42. A system comprising:

a processing device adapted to;

use a learned profile of an individual or group of individuals to determine the effect on future revenue of an organization resulting from at least one change in the individual or group of individuals, wherein the at least one change is selected from the group;

adding additional individuals to the group of individuals, replacing one individual for another individual, or eliminating an individual.