E-Commerce Consumer-Based Behavioral Target Marketing Reports

• US 20130035985A1
• Filed: 09/26/2011
• Published: 02/07/2013
• Est. Priority Date: 11/22/2006
• Status: Active Grant

• Current Assignee: Proclivity Media, Inc.
• Original Assignee: Proclivity Systems, Inc.
• Inventors: Gilbert, Sheldon
• Granted Patent: US 8,756,095 B2
• Time in Patent Office: Days
• US Class Current: 705/7.31
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• 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

Abstract

A system and methods which enable modeling of end consumer interests based on online activity and producing e-commerce reports is described. The method includes scoring and classifying interests and preferences of consumers in relation to various items being offered as function of time and utilizing such scores to predict purchasing activity and revenue yield for n-dimensional combinations of interest for generation of consumer lists for target marketing and merchandising. The method also includes converse modeling of the performance and behavioral profile of items offered as a function of consumer activity. This Abstract is provided for the sole purpose of complying with the rules that allow a reader to quickly ascertain the subject matter of the disclosure contained herein. This Abstract is submitted with the explicit understanding that it will not be used to interpret or to limit the scope or the meaning of the claims.

Claims

1. A computer-implemented method for predicting purchasing patterns by modeling the interests of consumers in products based on exhibited online shopping activity, comprising the steps of:

(a) collecting source data from a plurality of sources, wherein said source data includes at least;

order data, clickstream data, product data and customer data;

(b) aggregating said source data into a multi-dimensional, multi-resolutional, de-normalized interaction table;

(c) deriving a plurality of materialized, n-dimensional customer scores corresponding to said customer data from said multi-dimensional, multi-resolutional, de-normalized interaction table;

(d) deriving a plurality of run-time, n-dimensional customer scores corresponding to said customer data from multi-dimensional, multi-resolutional, de-normalized interaction table; and

(e) producing an e-commerce report, based on said plurality of materialized, n-dimensional customer scores and said plurality of run-time, n-dimensional customer scores, wherein said e-commerce report is used to determine the potential interests of consumers in the products being offered online.

2. The computer-implemented method of claim 1, wherein said product data relates to at least one of the following being offered online:

apparel;

content;

multi-media files;

consumer goods; and

services.

3. The computer-implemented method of claim 1, wherein said clickstream data relates to at least one of the following exhibited online consumer shopping activities:

browsing;

viewing;

cart inserting;

abandoning;

searching;

zooming;

price comparing;

reading;

purchasing;

gift wrapping;

emailing; and

shipping.

4. The computer-implemented method of claim 1, further comprising the steps of:

(f) utilizing a hierarchical Bayesian calculation to determine a plurality of materialized customer-product buying probabilities from said plurality of materialized n-dimensional customer scores; and

(g) utilizing a hierarchical Bayesian calculation to determine a plurality of run-time customer-product buying probabilities from said plurality of run-time, n-dimensional customer scores.

5. The computer-implemented method of claim 4, further comprising the step of:

(i) utilizing said e-commerce report to design a promotional campaign targeting a population of consumers corresponding to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.

6. The computer-implemented method of claim 4, wherein:

said e-commerce report is utilized to determine a population of consumers who should be targeted by a promotional campaign related to a known product; and

said population of consumers corresponds to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.

7. The computer-implemented method of claim 4, wherein:

said e-commerce report is utilized to determine at least one product that will be the subject of a promotional campaign targeting a known population of consumers; and

said known population of consumers corresponds to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.

8. A computer software product comprising a storage medium, wherein the storage medium contains processor executable instructions that, when executed by a processor, configure a computing apparatus to:

(a) collect source data from a plurality of sources, wherein said source data includes at least;

order data, clickstream data, product data and customer data;

(b) aggregate said source data into a multi-dimensional, multi-resolutional, de-normalized interaction table;

(c) derive a plurality of materialized, n-dimensional customer scores corresponding to said customer data from said multi-dimensional, multi-resolutional, de-normalized interaction table;

(d) derive a plurality of run-time, n-dimensional customer scores corresponding to said customer data from multi-dimensional, multi-resolutional, de-normalized interaction table; and

(e) produce an e-commerce report, based on said plurality of materialized, n-dimensional customer scores and said plurality of run-time, n-dimensional customer scores, wherein said e-commerce report is used to determine the potential interests of consumers in the products being offered online.

9. The computer software product of claim 8, wherein said product data relates to at least one of the following being offered online:

apparel;

content;

multi-media files;

consumer goods; and

services.

10. The computer software product of claim 8, wherein said clickstream data relates to at least one of the following exhibited online consumer shopping activities:

browsing;

viewing;

cart inserting;

abandoning;

searching;

zooming;

price comparing;

reading;

purchasing;

gift wrapping;

emailing; and

shipping.

11. The computer software product of claim 8, wherein the storage medium contains processor executable instructions that, when executed by the processor, further configure the computing apparatus to:

(f) utilize a hierarchical Bayesian calculation to determine a plurality of materialized customer-product buying probabilities from said plurality of materialized n-dimensional customer scores; and

(g) utilize a hierarchical Bayesian calculation to determine a plurality of run-time customer-product buying probabilities from said plurality of run-time, n-dimensional customer scores.

12. The computer software product of claim 11, wherein said e-commerce report is utilized to design a promotional campaign targeting a population of consumers corresponding to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.

13. The computer software product of claim 11, wherein:

said e-commerce report is utilized to determine a population of consumers who should be targeted by a promotional campaign related to a known product; and

said population of consumers corresponds to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.

14. The computer software product of claim 11, wherein:

said e-commerce report is utilized to determine at least one product that will be the subject of a promotional campaign targeting a known population of consumers; and

said known population of consumers corresponds to a subset of said plurality of materialized, customer-product buying probabilities and said plurality of real-time customer-product buying probabilities.