SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR SELECTING INTERNET-BASED ADVERTISING

• US 20070260520A1
• Filed: 01/18/2007
• Published: 11/08/2007
• Est. Priority Date: 01/18/2006
• Status: Abandoned Application

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Teracent Corporation (Alphabet Inc.)
• Inventors: Bector, Rajeev, Padala, Sailendra, Goenka, Vishal, Jha, Vikas, Papavassiliou, Vassilis
• Application Number:
  US11/624,618
• Publication Number:
  US 20070260520A1
• Time in Patent Office: Days
• US Class Current: 705/14.440
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0245 Surveys
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0274 Split fees

Abstract

Embodiments of a system method and computer program product for selecting an advertisement and presenting it to a user are described. Products and services offered by various merchants are read using a merchant specific catalog and stored in a common format. Categories for such products and services are normalized and virtual categories are created using various product attributes. Visual creatives, termed as ad-templates are created to control the visual and interactive aspects of the ad, including ad-size, color, as well as product attributes that are displayed in the ad. Ad-templates may be constrained to specific products or product categories. A learning algorithm uses an adaptive sampling process to sample various products, product categories and ad-templates independently for different learning units such as individual users, groups of users determined by some demographics, individual web pages and groups of web pages grouped using various similarity criteria. The performance of the ad is measured using various learning statistics, such as the click-through-rate, conversion rate, etc. The learning algorithm uses the learning statistics to optimize the return for the advertiser by favoring the products or categories that perform better on one or more specified criteria.

Claims

1. A method for selecting an advertisement, comprising:

sampling, over a time period, input received in response to the presentment of an advertisement;

using the sampled input to define a probability distribution model for an objective function representing one or more outcomes to the presentment of the advertisement;

selecting input values from the probability distribution model that optimize the objective function; and

generating content for an updated version of the advertisement based on the selected input values.

2. The method of claim 1, wherein the updated version of the advertisement is displayed to a view of a webpage.

3. The method of claim 1, wherein the sampled input includes at least one of:

attributes of goods and services associated with the advertisement, times when the advertisement is displayed, viewers of the advertisement, templates associated with the advertisement.

4. The method of claim 1, wherein the objective function is defined as a ratio of clicks on the advertisement to a number of times the advertisement is displayed.

5. The method of claim 1, wherein the objective function is defined as a ratio of advertisement commission paid by a merchant associated with the advertisement to a number of times the advertisement is displayed.

6. The method of claim 1, wherein the objective function is defined as a ratio of sales revenue shared by a merchant with an advertiser to a number of times that the advertisement is displayed.

7. The method of claim 1, wherein at least one of the input values selected from the probability distribution model has a highest confidence value in the probability distribution model for the objective function.

8. The method of claim 1, wherein at least one of the input values selected from the probability distribution model is selected to increase the confidence of the probability distribution model at the expense of maximizing the objective function.

9. The method of claim 1, wherein an advertising template is associated with the selected inputs to generate the content for the updated version of the advertisement.

10. The method of claim 9, wherein the advertising template controls presentation aspects of the content of the updated version of the advertisement.

11. The method of claim 9, wherein the advertising template is associated with attributes associated with the input.

12. The method of claim 1, wherein the objective function is calculated using one or more outcomes that are weighted to favor more recent outcomes over less recent outcomes.

13. A computer implemented system for selecting an advertisement, comprising:

an interface for sampling, over a time period, input received in response to the presentment of an advertisement;

a processor having;

a modeling module that uses the sampled input to define a probability distribution model for an objective function representing one or more outcomes to the presentment of the advertisement;

an optimizing module that selects input values from the probability distribution model that optimize the objective function; and

an advertisement generating module that generates content for an updated version of the advertisement based on the selected input various.

14. The system of claim 13, wherein the updated version of the advertisement is displayed to a view of a webpage.

15. The system of claim 13, wherein the sampled input includes at least one of:

attributes of goods and services associated with the advertisement, times when the advertisement is displayed, viewers of the advertisement, templates associated with the advertisement.

16. The system of claim 13, wherein the objective function is defined as a ratio of clicks on the advertisement to a number of times the advertisement is displayed.

17. The system of claim 13, wherein the objective function is defined as a ratio of advertisement commission paid by a merchant associated with the advertisement to a number of times the advertisement is displayed.

18. The system of claim 13, wherein the objective function is defined as a ratio of sales revenue shared by a merchant with an advertiser to a number of times that the advertisement is displayed.

19. The system of claim 13, wherein at least one of the input values selected from the probability distribution model has a highest confidence value in the probability distribution model for the objective function.

20. A computer program product embodied on a computer readable medium for causing a computer to perform a method, comprising:

computer code for sampling, over a time period, input received in response to the presentment of an advertisement;

computer code using the sampled input to define a probability distribution model for an objective function representing one or more outcomes to the presentment of the advertisement;

computer code selecting input values from the probability distribution model that optimize the objective function; and

computer code generating content for an updated version of the advertisement based on the selected input various.