System, Method, Software and Data Structure for Independent Prediction of Attitudinal and Message Responsiveness, and Preferences For Communication Media, Channel, Timing, Frequency, and Sequences of Communications, Using an Integrated Data Repository

• US 20130339093A1
• Filed: 11/29/2012
• Published: 12/19/2013
• Est. Priority Date: 06/30/2004
• Status: Active Grant

• Current Assignee: Experian Marketing Solutions, LLC (Experian plc)
• Original Assignee: Experian Marketing Solutions Incorporated (Experian plc)
• Inventors: Fanelli, Marc Christian, Gormley, Patricia Kay, Kulle, Kymberly Ann, Nocerino, Thomas G., Sanyal, Kaushik
• Granted Patent: US 9,471,928 B2
• Time in Patent Office: Days
• US Class Current: 705/7.33
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0203 Market surveys; Market polls
• CPC Class Codes: G06Q 30/0204 Market segmentation

Abstract

The present invention provides a system, method, software and data structure for independently predicting attitudinal and message responsiveness, using a plurality of attitudinal or other identification classifications and a plurality of message content or version classifications, for a selected population of a plurality of entities, such as individuals or households, represented in a data repository. The plurality of predictive attitudinal (or identification) classifications and plurality of predictive message content (ore version) classifications have been determined using a plurality of predictive models developed from a sample population and applied to a reference population represented in the data repository, such as attitudinal, behavioral, or demographic models. For each predictive attitudinal (or identification) classification, at least one predominant predictive message content or version classification is independently determined. The exemplary embodiments also provide, for each predictive attitudinal classification, corresponding information concerning predominant communication media (or channel) types, predominant communication timing, predominant communication frequency, and predominant communication sequencing.

Claims

1. A method for independently predicting attitudinal and message responsiveness for a selected population of a plurality of entities represented in a data repository, the method comprising:

(a) for each entity of the plurality of entities of the selected population, appending from the data repository a corresponding predictive attitudinal classification of a plurality of predictive attitudinal classifications and a corresponding plurality of memberships in a plurality of predictive message content classifications, the plurality of predictive attitudinal classifications and the plurality of predictive message content classifications having been determined using a plurality of predictive attitudinal models developed from a sample population and applied to a reference population represented in the data repository;

(b) for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, determining a penetration index of the selected population compared to the reference population; and

(c) for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, independently determining at least one predominant predictive message content classification from the appended corresponding plurality of memberships in the plurality of predictive message content classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

2. The method of claim 1, further comprising:

for each entity of the plurality of entities of the selected population, appending from the data repository at least one corresponding predictive communication media classification of a plurality of predictive communication media classifications, the corresponding predictive communication media classification having been determined from information stored in the data repository.

3. The method of claim 2, further comprising:

for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, independently determining at least one predominant predictive communication media classification from the appended plurality of predictive communication media classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

4. The method of claim 3, wherein the plurality of predictive communication media classifications comprises at least two of the following:

electronic mail (email), direct mail, telecommunication, radio, television, internet, satellite, cable media, video media, digital versatile disk media, compact disk media, print media, and visual display media.

5. The method of claim 1, further comprising:

for each entity of the plurality of entities of the selected population, appending from the data repository at least one corresponding predictive communication timing classification of a plurality of predictive communication timing classifications, the corresponding predictive communication timing classification having been determined from information stored in the data repository.

6. The method of claim 5, further comprising:

for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, independently determining at least one predominant predictive communication timing classification from the appended plurality of predictive communication timing classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

7. The method of claim 6, wherein the plurality of predictive communication timing classifications comprises at least two of the following communication timing classifications:

any time, morning, afternoon, evening, night, weekday, and weekend.

8. The method of claim 1, further comprising:

for each entity of the plurality of entities of the selected population, appending from the data repository at least one corresponding predictive communication frequency classification of a plurality of predictive communication frequency classifications, the corresponding predictive communication frequency classification having been determined from information stored in the data repository.

9. The method of claim 8, further comprising:

for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, independently determining at least one predominant predictive communication frequency classification from the appended plurality of predictive communication frequency classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

10. The method of claim 9, wherein the plurality of predictive communication frequency classifications comprises at least two of the following frequency classifications:

unlimited, none, daily, weekly, biweekly, monthly, semi-monthly, bimonthly, annually, and semi-annually.

11. The method of claim 1, further comprising:

for each entity of the plurality of entities of the selected population, appending from the data repository at least one corresponding predictive communication sequencing classification of a plurality of predictive communication sequencing classifications, the corresponding predictive communication sequencing classification having been determined from information stored in the data repository.

12. The method of claim 1, wherein the plurality of predictive message content classifications are determined by:

developing a plurality of empirical attitudinal factors based on a factor analysis of an attitudinal survey of the sample population;

using each empirical attitudinal factor of the plurality of empirical attitudinal factors, scoring each participant of the attitudinal survey to create a corresponding plurality of empirical attitudinal factor scores;

using a plurality of selected variables from the data repository as independent variables, and using the corresponding plurality of empirical attitudinal factor scores as dependent variables, performing a regression analysis to create the plurality of predictive attitudinal models; and

using each predictive attitudinal model of the plurality of predictive attitudinal models, scoring the plurality of entities represented in the data repository, as the reference population, to create the plurality of predictive message content classifications.

13. The method of claim 12, wherein the plurality of predictive attitudinal classifications are determined by a cluster analysis of the plurality of predictive message content classifications of each entity of the plurality of entities represented in the data repository.

14. The method of claim 1, further comprising:

determining at least one core attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively greater proportion of the selected population;

determining at least one niche attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively lesser proportion of the reference population; and

determining at least one growth attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively lesser penetration index and having a comparatively greater proportion of the reference population.

15. The method of claim 1, wherein the independent determination of at least one predominant predictive message content classification of step (c) further comprises:

for each predictive attitudinal classification, determining all of the appended corresponding plurality of memberships in the plurality of predictive message content classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification; and

for each predictive attitudinal classification, selecting at least one predictive message content classification, of the plurality of predictive message content classifications, corresponding to a comparatively greater number of entities of the selected population.

16. The method of claim 1, wherein the corresponding plurality of memberships in the plurality of predictive message content classifications are determined as a corresponding plurality of dichotomous variables.

17. The method of claim 1, wherein the corresponding plurality of memberships in the plurality of predictive message content classifications are determined as a corresponding plurality of probabilities.

18. The method of claim 1, wherein the corresponding plurality of memberships in the plurality of predictive message content classifications are determined as a corresponding plurality of scores from the plurality of predictive attitudinal models.

19. A system for independently predicting attitudinal and message responsiveness for a selected population of a plurality of entities, the system comprising:

a data repository storing, for each entity of a plurality of entities forming a reference population, a corresponding predictive attitudinal classification of a plurality of predictive attitudinal classifications and a corresponding plurality of memberships in a plurality of predictive message content classifications, the plurality of predictive attitudinal classifications and the plurality of predictive message content classifications having been determined using a plurality of predictive attitudinal models developed from a sample population and applied to the reference population; and

a processor coupled to the data repository, the processor configured to append from the data repository, for each entity of the plurality of entities of the selected population, the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications and the corresponding plurality of memberships in the plurality of predictive message content classifications;

for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, to determine a penetration index of the selected population compared to the reference population; and

for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, to independently determine at least one predominant predictive message content classification from the appended corresponding plurality of memberships in the plurality of predictive message content classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

20. The system of claim 19, wherein the processor is further configured to append from the data repository, for each entity of the plurality of entities of the selected population, at least one corresponding predictive communication media classification of a plurality of predictive communication media classifications, the corresponding predictive communication media classification having been determined from information stored in the data repository.

21. The system of claim 20, wherein the processor is further configured to independently determine, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive communication media classification from the appended plurality of predictive communication media classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

22. The system of claim 21, wherein the plurality of predictive communication media classifications comprises at least two of the following:

electronic mail (email), direct mail, telecommunication, radio, television, internet, satellite, cable media, video media, digital versatile disk media, compact disk media, print media, and visual display media.

23. The system of claim 19, wherein the processor is further configured to append from the data repository, for each entity of the plurality of entities of the selected population, at least one corresponding predictive communication timing classification of a plurality of predictive communication timing classifications, the corresponding predictive communication timing classification having been determined from information stored in the data repository.

24. The system of claim 23, wherein the processor is further configured to independently determine, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive communication timing classification from the appended plurality of predictive communication timing classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

25. The system of claim 24, wherein the plurality of predictive communication timing classifications comprises at least two of the following communication timing classifications:

any time, morning, afternoon, evening, night, weekday, and weekend.

26. The system of claim 19, wherein the processor is further configured to append from the data repository, for each entity of the plurality of entities of the selected population, at least one corresponding predictive communication frequency classification of a plurality of predictive communication frequency classifications, the corresponding predictive communication frequency classification having been determined from information stored in the data repository.

27. The system of claim 26, wherein the processor is further configured to independently determine, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive communication frequency classification from the appended plurality of predictive communication frequency classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

28. The system of claim 27, wherein the plurality of predictive communication frequency classifications comprises at least two of the following frequency classifications:

unlimited, none, daily, weekly, biweekly, monthly, semi-monthly, bimonthly, annually, and semi-annually.

29. The system of claim 19, wherein the processor is further configured to determine the selected population of the plurality of entities by matching a listing of a plurality of customers to the reference population represented in the data repository.

30. The system of claim 19, wherein the processor is further configured to determine the plurality of predictive message content classifications by developing a plurality of empirical attitudinal factors based on a factor analysis of an attitudinal survey of the sample population;

to score each participant of the attitudinal survey, using each empirical attitudinal factor of the plurality of empirical attitudinal factors, to create a corresponding plurality of empirical attitudinal factor scores;

using a plurality of selected variables from the data repository as independent variables, and using the corresponding plurality of empirical attitudinal factor scores as dependent variables, to perform a regression analysis to create the plurality of predictive attitudinal models; and

using each predictive attitudinal model of the plurality of predictive attitudinal models, to score the plurality of entities represented in the data repository, as the reference population, to create the plurality of predictive message content classifications.

31. The system of claim 30, wherein the processor is further configured to determine the plurality of predictive attitudinal classifications by performing a cluster analysis of the plurality of predictive message content classifications of each entity of the plurality of entities represented in the data repository.

32. The system of claim 19, wherein the processor is further configured to determine at least one core attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively greater proportion of the selected population;

to determine at least one niche attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively lesser proportion of the reference population; and

to determine at least one growth attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively lesser penetration index and having a comparatively greater proportion of the reference population.

33. The system of claim 19, wherein the processor is further configured to independently determine the at least one predominant predictive message content classification by determining, for each predictive attitudinal classification, all of the appended corresponding plurality of memberships in the plurality of predictive message content classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification;

and selecting, for each predictive attitudinal classification, at least one predictive message content classification, of the plurality of predictive message content classifications, corresponding to a comparatively greater number of entities of the selected population.

34. The system of claim 19, wherein the processor is further configured to determine the corresponding plurality of memberships in the plurality of predictive message content classifications as a corresponding plurality of dichotomous variables, as a corresponding plurality of probabilities, or as a corresponding plurality of scores from the plurality of predictive attitudinal models.

35. A tangible medium storing computer readable software for independently predicting attitudinal and message responsiveness for a selected population of a plurality of entities represented in a data repository, the tangible medium storing computer readable software comprising:

a first program construct for appending from the data repository, for each entity of the plurality of entities of the selected population, a corresponding predictive attitudinal classification of a plurality of predictive attitudinal classifications and a corresponding plurality of memberships in a plurality of predictive message content classifications, the plurality of predictive attitudinal classifications and the plurality of predictive message content classifications having been determined using a plurality of predictive attitudinal models developed from a sample population and applied to a reference population represented in the data repository;

a second program construct for determining, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, a penetration index of the selected population compared to the reference population; and

a third program construct for independently determining, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive message content classification from the appended corresponding plurality of memberships in the plurality of predictive message content classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

36. The tangible medium storing computer readable software of claim 35, further comprising:

a fourth program construct for appending from the data repository, for each entity of the plurality of entities of the selected population, at least one corresponding predictive communication media classification of a plurality of predictive communication media classifications, the corresponding predictive communication media classification determined from information stored in the data repository.

37. The tangible medium storing computer readable software of claim 36, further comprising:

a fifth program construct for independently determining, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive communication media classification from the appended plurality of predictive communication media classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

38. The tangible medium storing computer readable software of claim 37, wherein the plurality of predictive communication media classifications comprises at least two of the following:

electronic mail (email), direct mail, telecommunication, radio, television, internet, video media, digital versatile disk media, print media, and visual display media.

39. The tangible medium storing computer readable software of claim 35, further comprising:

a sixth program construct for appending from the data repository, for each entity of the plurality of entities of the selected population, at least one corresponding predictive communication timing classification of a plurality of predictive communication timing classifications, the corresponding predictive communication timing classification determined from information stored in the data repository.

40. The tangible medium storing computer readable software of claim 39, further comprising:

a seventh program construct for independently determining, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, independently determining at least one predominant predictive communication timing classification from the appended plurality of predictive communication timing classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

41. The tangible medium storing computer readable software of claim 40, wherein the plurality of predictive communication timing classifications comprises at least two of the following communication timing classifications:

any time, morning, afternoon, evening, night, weekday, and weekend.

42. The tangible medium storing computer readable software of claim 35, further comprising:

an eighth program construct for appending from the data repository, for each entity of the plurality of entities of the selected population, appending from the data repository at least one corresponding predictive communication frequency classification of a plurality of predictive communication frequency classifications, the corresponding predictive communication frequency classification determined from information stored in the data repository.

43. The tangible medium storing computer readable software of claim 42, further comprising:

a ninth program construct for independently determining, for each predictive attitudinal classification of the plurality of predictive attitudinal classifications, at least one predominant predictive communication frequency classification from the appended plurality of predictive communication frequency classifications of the plurality of entities of the selected population having the corresponding predictive attitudinal classification of the plurality of predictive attitudinal classifications.

44. The tangible medium storing computer readable software of claim 43, wherein the plurality of predictive communication frequency classifications comprises at least two of the following frequency classifications:

unlimited, none, daily, weekly, biweekly, monthly, semi-monthly, bimonthly, annually, and semi-annually.

45. The tangible medium storing computer readable software of claim 35, further comprising a tenth program construct for determining the plurality of predictive message content classifications by:

developing a plurality of empirical attitudinal factors based on a factor analysis of an attitudinal survey of the sample population;

using each empirical attitudinal factor of the plurality of empirical attitudinal factors, scoring each participant of the attitudinal survey to create a corresponding plurality of empirical attitudinal factor scores;

using a plurality of selected variables from the data repository as independent variables, and using the corresponding plurality of empirical attitudinal factor scores as dependent variables, performing a regression analysis to create the plurality of predictive attitudinal models; and

using each predictive attitudinal model of the plurality of predictive attitudinal models, scoring the plurality of entities represented in the data repository, as the reference population, to create the plurality of predictive message content classifications.

46. The tangible medium storing computer readable software of claim 45, further comprising an eleventh program construct for determining the plurality of predictive attitudinal classifications by a cluster analysis of the plurality of predictive message content classifications of each entity of the plurality of entities represented in the data repository.

47. The tangible medium storing computer readable software of claim 35, further comprising:

a twelfth program construct for determining at least one core attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively greater proportion of the selected population;

for determining at least one niche attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively greater penetration index and having a comparatively lesser proportion of the reference population; and

for determining at least one growth attitudinal classification by selecting, from the plurality of predictive attitudinal classifications, at least one predictive attitudinal classification having a comparatively lesser penetration index and having a comparatively greater proportion of the reference population.