Bid adjustment scheduling for electronic advertising

• US 8,719,081 B1
• Filed: 11/10/2008
• Issued: 05/06/2014
• Est. Priority Date: 11/10/2008
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Snyder, Luke A., Herrmann, Eric Alfred, Langrock, David J., Reid, Robert Lockhart
• Primary Examiner(s): Lastra, Daniel
• Application Number:
  US12/267,833
• Time in Patent Office: 2,003 Days
• Field of Search: 705/14.1
• US Class Current: 705/14.1
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 90/00 Systems or methods specially adapted for administrative, commercial, financial, managerial or supervisory purposes, not involving significant data processing

Abstract

Bid amounts for electronic advertising can be adjusted throughout the day, or for different days, according to a day parting schedule based on factors such as variations in efficiency. For any set of advertisements grouped based on factors such as keyword, landing page, geographic location, user demographic, etc., values can be forecast for each time period throughout the day. A variation threshold is used to group adjacent periods of time into partitions, and the threshold can be varied until the number of partitions meets the requirements of the provider with whom the advertisement is to be placed. An adjustment factor can be determined for each partition using the forecast information, and these factors can be uploaded to the provider to adjust the base bid price for any advertisement in that group at the appropriate times throughout the day.

Claims

1. A computer-implemented method of adjusting a bid price for an advertisement in an electronic environment, comprising:

under the control of one or more computer systems configured with executable instructions,

selecting a group of advertisements corresponding to a class of keywords for a provider operable to cause each of the advertisements to be displayed with a respective keyword;

determining a time interval corresponding to a minimum adjustment period for the provider;

computing a forecast advertising efficiency for each of a plurality of time intervals throughout a day for the group of advertisements;

starting with a first time interval in the day, grouping the plurality of time intervals into a plurality of partitions, each partition including adjacent time intervals with an average forecast advertising efficiency that does not exceed a variation threshold with respect to a forecast advertising efficiency for any of the included time intervals;

if the number of partitions does not meet an acceptable number of partitions for the provider, adjusting the variation threshold and regrouping the plurality of time intervals until the number of partitions meets an acceptable number of partitions; and

submitting a schedule of bid adjustments to the provider for the class of keywords, the bid adjustments computed to be applied to a base bid price for any of the plurality of advertisements when one of the plurality of advertisements is selected to be displayed for one of the class of keywords, each bid adjustment corresponding to the time intervals and average forecast advertising efficiency included in a respective partition.

2. A method according to claim 1, wherein:

the provider is a search engine operable to receive any of the class of keywords from at least one user and generate a page of search results in response thereto, the page of search results being configured to include at least one ad selected based on an adjusted bid price.

3. A method according to claim 2, wherein:

the provider applies the bid adjustment to a base bid for each advertisement to determine the adjusted bid price before selecting at least one ad to be displayed for the page.

4. A computer-implemented method of adjusting a bid price for an advertisement in an electronic environment, comprising:

under the control of one or more computer systems configured with executable instructions,

computing an estimated advertising efficiency for each of a plurality of time intervals throughout a day for a plurality of advertisements having at least one common aspect;

grouping the plurality of time intervals into a plurality of partitions, each partition including adjacent time intervals with an average estimated advertising efficiency that does not exceed a variation threshold with respect to the estimated advertising efficiency for any of the included time intervals;

if the number of partitions does not meet an acceptable number of partitions, adjusting the variation threshold and regrouping the plurality of time intervals until the number of partitions meets an acceptable number of partitions; and

submitting a set of bid adjustments to be applied to a base bid price for each of the plurality of advertisements, each bid adjustment corresponding to the time intervals and average estimated advertising efficiency included in a respective partition.

5. A method according to claim 4, wherein:

the estimated advertising efficiency is a function of a forecast advertising efficiency versus a target advertising efficiency for the plurality of advertisements.

6. A method according to claim 5, wherein:

the forecast advertising efficiency is function of a forecast spend versus a forecast gross revenue.

7. A method according to claim 4, wherein:

multiple sets of bid adjustments are generated, each set corresponding to at least one of a different provider, a different geographic region, and a different category of keywords.

8. A method according to claim 4, wherein:

the set of bid adjustments is submitted to a provider of electronic content operable to adjust the base bid price for each advertisement based on the corresponding bid adjustments.

9. A method according to claim 8, wherein:

the provider specifies at least one of a minimum time interval and an allowed number of partitions.

10. A method according to claim 4, wherein:

a set of bid adjustments includes a schedule of adjustments for each day of an upcoming week.

11. A method according to claim 4, further comprising:

monitoring bid adjustments over time; and

ensuring that bid adjustments do not exceed a maximum adjustment threshold.

12. A method according to claim 4, wherein:

the plurality of advertisements having at least one common aspect correspond to a class of keywords for a provider operable to cause each of the advertisements to be displayed with a respective keyword.

13. A method according to claim 4, wherein:

the estimated advertising efficiency is based on a weighted average of bid data for the same time interval in at least one of previous weeks and previous years.

14. A method according to claim 4, further comprising:

determining the base bid price for each advertisement.

15. A method according to claim 4, further comprising:

determining an adjustment factor that will result in a bid price for a selected partition not being selected by a provider when the estimated average advertising efficiency for that partition falls below a minimum efficiency threshold.

16. A method according to claim 4, further comprising:

maintaining a list of advertisements for which no bid adjustment is to be submitted.

17. A system for adjusting a bid price for an advertisement in an electronic environment, comprising:

a processor; and

a memory device including instructions that, when executed by the processor, cause the processor to;

determine an estimated advertising efficiency for each of a plurality of time intervals throughout a day for a plurality of advertisements;

group the plurality of time intervals into a plurality of partitions, each partition including adjacent time intervals with an average estimated advertising efficiency that does not exceed a variation threshold with respect to an estimated advertising efficiency for any of the included time intervals;

if the number of partitions does not meet an acceptable number of partitions, adjust the variation threshold and regrouping the plurality of time intervals until the number of partitions meets an acceptable number of partitions; and

submit a set of bid adjustments to be applied to a base bid price for each of the plurality of advertisements, each bid adjustment corresponding to the time intervals and average estimated advertising efficiency included in a respective partition.

18. A system according to claim 17, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

generate multiple sets of bid adjustments, each set corresponding to at least one of a different provider, a different geographic region, and a different category of keywords.

19. A system according to claim 17, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

submit the set of bid adjustments a provider of electronic content operable to adjust the base bid price for each advertisement based on the corresponding bid adjustments.

20. A system according to claim 17, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

monitor bid adjustments over time; and

ensure that bid adjustments do not exceed a maximum adjustment threshold.

21. A system according to claim 17, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

determine the estimated advertising efficiency based at least in part on a weighted average of bid data for the same time interval in at least one of previous weeks and previous years.

22. A system according to claim 17, wherein the memory further includes instructions that, when executed by the processor, cause the processor to:

determine an adjustment factor will result in a bid price for a selected partition not being selected by a provider when the estimated average advertising efficiency for that partition falls below a minimum efficiency threshold.

23. A computer program product embedded in a computer readable storage medium for adjusting a bid price for an advertisement in an electronic environment, comprising:

program code executable by one or more processors for computing an estimated advertising efficiency for each of a plurality of time intervals throughout a day for a plurality of advertisements having at least one common aspect;

program code executable by the one or more processors for grouping the plurality of time intervals into a plurality of partitions, each partition including adjacent time intervals with an average estimated advertising efficiency that does not exceed a variation threshold with respect to an estimated advertising efficiency for any of the included time intervals;

program code executable by the one or more processors for, if the number of partitions does not meet an accepted number of partitions, adjusting the variation threshold and regrouping the plurality of time intervals until the number of partitions meets an accepted number of partitions; and

program code executable by the one or more processors for submitting a set of bid adjustments to be applied to a base bid price for each of the plurality of advertisements, each bid adjustment corresponding to the time intervals and average estimated advertising efficiency included in a respective partition.

24. A computer program product according to claim 23, further comprising:

program code executable by the one or more processors for generating multiple sets of bid adjustments, each set corresponding to at least one of a different provider and a different geographic region.

25. A computer program product according to claim 23, further comprising:

program code executable by the one or more processors for monitoring bid adjustments over time; and

program code executable by the one or more processors for ensuring that bid adjustments do not exceed a maximum adjustment threshold.