SYSTEM AND METHOD FOR AUTOMATING MARKET ANALYSIS FROM ANONYMOUS BEHAVIOR PROFILES

• US 20090248496A1
• Filed: 04/01/2009
• Published: 10/01/2009
• Est. Priority Date: 04/01/2008
• Status: Active Application

• Current Assignee: Certona Corporation (StartApp, Inc.)
• Original Assignee: Certona Corporation (StartApp, Inc.)
• Inventors: Hueter, Geoffrey J., Quandt, Steven C.
• Granted Patent: US 10,290,039 B2
• Time in Patent Office: Days
• US Class Current: 705/10
• 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, such as aesthetic response, preference, interest, or relevancy, are explicitly submitted by subjects or derived implicitly from visitor interactions with the objects. Objects include movies, books, songs, commercial products, news articles, advertisements or any other type of content or physical item. A profiling engine processes the ratings information and generates compact profiles of each subject and object based on the 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 physical attributes, such as predicting demographic or personality traits or subjective or other descriptive attributes of objects, such as size, shape, color, hipness, or trendiness. 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 automating market analysis from anonymous behavior profiles, comprising:

(a) a service system to collect, profile and classify subject behavior;

(b) subjects and objects that are represented in vector form;

(c) distribution analysis;

(d) market analysis; and

(e) attribute prediction

whereby said system automatically generates profiles of subjects and objects from subject object interactions and projects those self-derived profiles back to known attributes of sub-populations of subjects and objects,

all accomplished in a non-invasive, mentor-less and scalable fashion, scalable to large numbers of users and objects.

2. The system for automating market analysis from anonymous behavior profiles, according to claim 1, wherein said market analysts includes market analysis of a subset of subjects or objects, or market segments.

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

4. The system for automating market analysis from anonymous behavior profiles, according to claim 1, wherein said distribution analysis includes analysis of the distributions of measured affinities and predicted, affinities from matching subject and object vectors.

5. The system for automating market analysis from anonymous behavior profiles, according to claim 4, wherein said distribution analysis includes comparing an object'"'"'s distribution of predicted affinities to the object'"'"'s distribution of reported affinities to assess the awareness of the population of receptive subjects to that object.

6. The system for automating market analysis from anonymous behavior profiles, according to claim 4, wherein said distribution analysis includes measuring the breadth of subject object affinities for an object to assess whether the object elicits strong or neutral reactions from the population of subjects.

7. The system for automating market analysis from anonymous behavior profiles, according to claim 1, wherein said attribute prediction includes predictive models of demographic, psychographic, and other subject attributes from said subject vector profiles.

8. The system for automating market analysis from anonymous behavior profiles, according to claim 7, wherein said predictive models include linear regression, neural networks, CART, and other supervised learning techniques.

9. The system for automating market analysis from anonymous behavior profiles, according to claim 1, wherein said market analysis Includes identifying target market attributes from the nominal, or typical, characteristics of a cluster of subject vector profiles.

10. The system for automating market analysis from anonymous behavior profiles, according to claim 9, wherein said market analysis includes market segmentation that combines known subject attributes and data-derived subject vector profiles.

11. A method for automating market analysis from anonymous behavior profiles, comprising the steps of:

(a) providing a service system to collect, profile and classify subject behavior;

(b) providing subjects and objects that are represented in vector form;

(c) performing distribution analysis;

(d) performing market analysis; and

(e) performing attribute prediction

whereby said system automatically generates profiles of subjects and objects from subject object interactions and projects those self-derived profiles back to known attributes of sub-populations of subjects and objects,

all accomplished in a non-invasive, mentor-less and scalable fashion, scalable to large numbers of users and objects.

12. The method for automating market analysis from anonymous behavior profiles, according to claim 11, wherein said step of performing market analysis includes the step of performing market analysis wherein said market analysis includes market analysis of a subset of subjects or objects, or market segments.

13. The method for automating market analysis from anonymous behavior profiles, according to claim 11, wherein said step of providing subjects and objects that are represented in vector form includes the step of providing subjects and objects represented in vector form wherein said subject and object vectors include subject and object vectors derived from anonymous website browsing behavior.

14. The method for automating market analysis from anonymous behavior profiles, according to claim 11, wherein said step of performing distribution analysis includes the step of performing distribution wherein said distribution analysis includes analysis of the distributions of measured affinities and predicted affinities from matching subject and object vectors, and further wherein said distribution analysis includes comparing an object'"'"'s distribution of predicted affinities to the object'"'"'s distribution of reported affinities to assess the awareness of the population of receptive subjects to that object.

15. The method for automating market analysis from anonymous behavior profiles, according to claim 14, wherein said step of performing distribution analysis by comparing an object'"'"'s distribution of predicted affinities to the object'"'"'s distribution of reported affinities includes the step of performing distribution analysis by comparing an object'"'"'s distribution of predicted affinities to the object'"'"'s distribution of reported affinities wherein said distribution analysis includes measuring the breadth of subject object affinities for an object to assess whether the object elicits strong or neutral reactions from the population of subjects.

16. The method for automating market analysis from anonymous behavior profiles, according to claim 14, wherein said step of performing attribute prediction includes the step of performing attribute prediction wherein said attribute prediction includes predictive models of demographic, psychographic, and other subject attributes from said subject vector profiles, and further wherein said predictive models include linear regression, neural networks, CART, and other supervised learning techniques.

17. The method for automating market analysis from anonymous behavior profiles, according to claim 11, wherein said step of performing market analysis includes the step of performing market analysis wherein said market analysis includes identifying target market attributes from the nominal, or typical, characteristics of a cluster of subject vector profiles.

18. The method for automating market analysis from anonymous behavior profiles, according to claim 17, wherein said step of performing market analysis includes the step of performing market analysis wherein said market analysis includes a market segmentation calculation that combines known subject attributes and data-derived subject vector profiles.

19. A method for using a system for automating market analysis from anonymous behavior profiles, comprising the steps of;

(a) obtaining an object'"'"'s profile vector;

(b) matching the object vector to a population of subject vectors to produce predicted affinities of subjects to the object;

(c) computing the distributions of predicted and recorded affinities;

(d) comparing predicted and recorded affinity distributions;

(e) clustering vectors; and

(f) identifying a target market.

20. The method for automating market analysis from anonymous behavior profiles, according to claim 19, wherein said step of identifying a target market includes the step of identifying a target market for a musical artist.