System and method for automating market analysis from anonymous behavior profiles

• US 10,290,039 B2
• Filed: 04/01/2009
• Issued: 05/14/2019
• Est. Priority Date: 04/01/2008
• Status: Active Grant

• Current Assignee: Certona Corporation (StartApp, Inc.)
• Original Assignee: Certona Corporation (StartApp, Inc.)
• Inventors: Hueter, Geoffrey J., Quandt, Steven C.
• Primary Examiner(s): Goldberg, Ivan R
• Application Number:
  US12/416,524
• Publication Number:
  US 20090248496A1
• Time in Patent Office: 3,695 Days
• Field of Search: None
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0185 Product, service or business identity fraud
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities
• CPC Class Codes: G06Q 30/0204 Market segmentation
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: H04L 51/212 using filtering or selective blocking

Abstract

A system and method is disclosed for profiling subjects and objects based on subjects'"'"' responses to various objects, for purposes of determining and presenting the objects most likely to generate the most likely response from each visitor. Object ratings are explicitly submitted by subjects or derived implicitly from visitor interactions with the objects. A profiling engine processes the ratings information and generates compact profiles of each subject and object based on similarities and differences in affinities between the group of subjects and the group of objects. The object profiles can be clustered to create behavioral object categories. Additionally, a modeling module inverts the abstract subject and object profiles into marketing attributes. The system has application in market analysis and segmentation, behavioral targeting, product placement, and online advertising, to name but a few applications.

Claims

1. A system for digital media engagement, comprising:

a web-based computer system and network configured as;

(a) an application client which presents media options as objects to system users, wherein said system users are subjects, and measures and collects affinities of said subjects to said objects as actual affinities A, and further wherein said application client transmits said affinities to a recommendation server across said network;

(b) the recommendation server which represents and stores a profile of a said subject as a subject vector S, and a profile of a said object as an object vector B, such that a predicted affinity P of the subject to the object is generated by matching the subject vector to the object vector according to the dot product of S and B;

(c) a profiler of said recommendation server which trains the subject vectors and object vectors as a minimization of a cost function, E, based on the differences between the predicted and actual affinities of the subjects for the objects, for which actual affinities have been measured and stored in at least one database of the recommendation server, wherein the recommendation server starts with subject and object vectors of a specified number of dimensions, N, which values of the dimensions of the subject and object vectors are initially set to random values;

then the object vectors are fixed and the subject vectors are updated to minimize the cost function, E;

then the subject vectors are fixed and the object vectors are updated to minimize the cost function, E; and

the above steps of fixing the object vectors and updating the subject vectors and then fixing the subject vectors and updating the object vectors are repeated until the change in the decrease of the cost function at the end of the update of the object vectors for that iteration is less than a specified limit, and the resulting trained subject vectors and object vectors are updated in the at least one database of the recommendation server;

whereby said cost function, E, is the mean squared error between the predicted affinities and the actual affinities;

2. The system for digital media engagement, according to claim 1, wherein said select subjects includes selecting all of the subjects, subjects that meet certain criteria, or a random sample.

3. The system for digital media engagement, according to claim 1, wherein said subject and object profiles include subject and object vectors derived from anonymous website browsing behavior.

4. The system for digital media engagement, according to claim 1, wherein said measure the affinities of subjects to objects includes measuring affinities as explicit ratings of the objects by the subjects.

5. The system for digital media engagement, according to claim 1, wherein said measure the affinities of subjects to objects includes measuring the affinity of a subject to an object based on a level of interaction of the subject to the object.

6. The system for digital media engagement, according to claim 1, wherein said predicted affinity of a subject to an object is generated by matching the subject vector to the object vector includes matching the subject vector to the object vector using a Euclidean distance between the subject vector and the object vector.

7. The system for digital media engagement, according to claim 1, wherein said classify said object according to the breadth of said distribution of predicted affinities includes determining the breadth of distribution of affinities by histogram or moments.

8. The system for digital media engagement, according to claim 1, wherein said object that has a breadth of distribution of said predicted affinities above a specified breadth threshold is classified as REACTIVE and said object that has a breadth of distribution of said predicted affinities below a specified threshold is classified as INERT.

9. The system for digital media engagement, according to claim 1, whereby only objects with said breadth of distribution below a specified breadth threshold are presented to users as recommended options.

10. A system for digital media engagement, comprising:

a web-based computer system and network configured to include;

(a) an application client which presents media options as objects to system users, wherein said system users are subjects, and measures and collects affinities of said subjects to said objects as actual affinities A, and further wherein said application client transmits said affinities to a recommendation server across said network;

(b) the recommendation server which represents and stores a profile of a said subject as a subject vector, S, and a profile of a said object as an object vector, B, such that a predicted affinity, P, of the subject to the object is generated by matching the subject vector to the object vector according to the dot product of S and B;

(c) a profiler of said recommendation server which trains the subject vectors and object vectors as a minimization of a cost function E, based on the differences between the predicted and actual affinities of the subjects for the objects for which actual affinities have been measured and stored in at least one database of the recommendation server, the recommendation server starts with subject and object vectors of a specified number of dimensions, N, which values of the dimensions of the subject and object vectors are initially set to random values;

then the object vectors are fixed and the subject vectors are updated to minimize the cost function, E;

then the subject vectors are fixed and the object vectors are updated to minimize the cost function, E; and

the above steps of fixing the object vectors and updating the subject vectors and then fixing the subject vectors and updating the object vectors are repeated until the change in the decrease of the cost function at the end of the update of the object vectors for that iteration is less than a specified limit, and the resulting trained subject vectors and object vectors are updated in the at least one database of the recommendation server;

whereby said cost function, E, is the mean squared error between the predicted affinities and the actual affinities;

11. The system for digital media engagement, according to claim 10, wherein said select subjects includes selecting all of the subjects, subjects that meet certain criteria, or a random sample.

12. The system for digital media engagement, according to claim 10, wherein said subject and object profiles include subject and object vectors derived from anonymous website browsing behavior.

13. The system for digital media engagement, according to claim 10, wherein said measure the affinities of subjects to objects includes measuring affinities as explicit ratings of the objects by the subjects.

14. The system for digital media engagement, according to claim 10, wherein said measure the affinities of subjects to objects includes measuring the affinity of a subject to an object based on a level of interaction of the subject to the object.

15. The system for digital media engagement, according to claim 10, wherein said predicted affinity of a subject to an object is generated by matching the subject vector to the object vector includes matching the subject vector to the object vector using a Euclidean distance between the subject vector and the object vector.

16. The system for digital media engagement, according to claim 10, whereby objects with said level of awareness below a specified awareness threshold are presented as recommended options to those users who have not provided actual affinities for said objects and have predicted affinities for said objects above a specified affinity threshold.

17. The system for digital media engagement, according to claim 10, wherein said object having an awareness level above a specified awareness threshold for a group of subjects is classified as MINDSHARE, and said object having an awareness level below a specified awareness threshold for a group of subjects is classified as UNDISCOVERED.