Automatic adjustment of advertiser bids to equalize cost-per-conversion among publishers for an advertisement

• US 8,346,607 B1
• Filed: 04/02/2012
• Issued: 01/01/2013
• Est. Priority Date: 07/30/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Benson, Scott S., Tong, Simon
• Primary Examiner(s): Rosen, Elizabeth
• Assistant Examiner(s): GOODBODY, JOAN T
• Application Number:
  US13/437,173
• Time in Patent Office: 274 Days
• Field of Search: 705/14.71
• US Class Current: 705/14.71
• CPC Class Codes: G06Q 10/025 Coordination of plural reservations, e.g. plural trip segments, transportation combined with accommodation
• CPC Class Codes: G06Q 20/105 involving programming of a portable memory device, e.g. IC cards, "electronic purses"
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 40/08 Insurance

Abstract

A learning model is built on a combination of advertiser, publisher and user data. The learning model can be applied to all advertisers in an advertising system. The learning model provides predicted conversion rates for a given advertisement (“ad”) appearing on different publisher networks. A predicted conversion rate represents the probability that a click on a given ad appearing on a given publisher will lead to a conversion. The predicted conversion rates are used to generate a multiplier. The multiplier is used to automatically adjust the advertiser'"'"'s bid (e.g., maximum cost-per-click (CPC)) for the given ad prior to an auction for the ad. Adjusting the advertiser'"'"'s bid equalizes a cost-per-conversion among the publishers for the ad.

Claims

1. A computer-implemented method comprising:

accessing bid data specifying an advertiser'"'"'s initial bid for placement of an advertisement on a publisher resource;

accessing data specifying a first predicted conversion rate for placement of the advertisement on a first publisher resource and a second predicted conversion rate for placement of the advertisement on a second publisher resource different from the first publisher resource;

determining, by one or more data processors, a multiplier based at least in part on the first and second predicted conversion rates; and

adjusting, by the one or more data processors, the initial bid for placement of the advertisement on the first publisher resource using the multiplier to equalize a first cost-per-conversion specifying a first predicted cost to realize a conversion from placement of the advertisement on the first publisher resource to a second cost-per-conversion specifying a second predicted cost to realize a conversion from placement of the advertisement on the second publisher resource, wherein;

the first predicted cost is based on the adjusted bid and the first predicted conversion rate; and

the second predicted cost is based on the initial bid and the second predicted conversion rate, and the first predicted cost is the same as the second predicted cost.

2. The method of claim 1, wherein determining the multiplier comprises determining the multiplier based at least in part on a ratio of the first predicted conversion rate to the second predicted conversion rate.

3. The method of claim 2, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises decreasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being less than the second predicted conversion rate.

4. The method of claim 2, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises increasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being greater than the second predicted conversion rate.

5. The method of claim 2, wherein adjusting the initial bid comprises multiplying the initial bid by the multiplier.

6. The method of claim 1, wherein accessing data specifying a first predicted conversion rate and a second predicted conversion rate comprises:

determining the first predicted conversion rate and the second predicted conversion rate using a learning model developed from a combination of advertiser, publisher and user data.

7. The method of claim 6, further comprising:

developing the learning model using a historical predicted conversion rate associated with at least one of the first publisher resource or the second publisher resource.

8. The method of claim 1, wherein the advertiser'"'"'s initial bid is a cost-per-click bid.

9. A computer-implemented method comprising:

obtaining a first predicted conversion rate for an advertisement appearing on a first publisher property;

obtaining a second predicted conversion rate for the advertisement appearing on a second different publisher property;

computing, by one or more data processors, a multiplier using the first and second predicted conversion rates, wherein the multiplier is based at least in part on a function of a probability that a conversion will result from a selection of the advertisement by a user on the first publisher property with respect to a probability that a conversion will result from a selection of the advertisement by a user on the second publisher property; and

automatically adjusting a bid of an advertiser associated with the advertisement using the multiplier to equalize a cost-per-conversion for the advertisement between the first and second publisher properties.

10. The method of claim 9, wherein the advertiser'"'"'s bid is a maximum cost-per-click bid.

11. The method of claim 9, where automatically adjusting a bid comprises:

automatically multiplying the a maximum cost-per-click bid by the multiplier.

12. A non-transitory computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, causes the one or more processors to perform operations comprising:

accessing bid data specifying an advertiser'"'"'s initial bid for placement of an advertisement on a publisher resource;

accessing data specifying a first predicted conversion rate for placement of the advertisement on a first publisher resource and a second predicted conversion rate for placement of the advertisement on a second publisher resource different from the first publisher resource;

determining a multiplier based at least in part on the first and second predicted conversion rates; and

adjusting the initial bid for placement of the advertisement on the first publisher resource using the multiplier to equalize a first cost-per-conversion specifying a first predicted cost to realize a conversion from placement of the advertisement on the first publisher resource to a second cost-per-conversion specifying a second predicted cost to realize a conversion from placement of the advertisement on the second publisher resource, wherein;

the first predicted cost is based on the adjusted bid and the first predicted conversion rate; and

the second predicted cost is based on the initial bid and the second predicted conversion rate and the first predicted cost is the same as the second predicted cost.

13. The non-transitory computer-readable storage medium of claim 12, wherein determining the multiplier comprises determining the multiplier based at least in part on a ratio of the first predicted conversion rate to the second predicted conversion rate.

14. The non-transitory computer-readable storage medium of claim 13, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises decreasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being less than the second predicted conversion rate.

15. The non-transitory computer-readable storage medium of claim 13, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises increasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being greater than the second predicted conversion rate.

16. The non-transitory computer-readable storage medium of claim 13, wherein adjusting the initial bid comprises multiplying the initial bid by the multiplier.

17. The non-transitory computer-readable storage medium of claim 12, wherein the advertiser'"'"'s initial bid is a cost-per-click bid.

18. A system comprising:

one or more data processors; and

software stored on a computer storage apparatus and comprising instructions executable by the one or more data processors and upon such execution cause the one or more data processors to perform operations comprising;

accessing bid data specifying an advertiser'"'"'s initial bid for placement of an advertisement on a publisher resource;

accessing data specifying a first predicted conversion rate for placement of the advertisement on a first publisher resource and a second predicted conversion rate for placement of the advertisement on a second publisher resource different from the first publisher resource;

determining a multiplier based at least in part on the first and second predicted conversion rates; and

adjusting the initial bid for placement of the advertisement on the first publisher resource using the multiplier to equalize a first cost-per-conversion specifying a first predicted cost to realize a conversion from placement of the advertisement on the first publisher resource to a second cost-per-conversion specifying a second predicted cost to realize a conversion from placement of the advertisement on the second publisher resource, wherein;

the first predicted cost is based on the adjusted bid and the first predicted conversion rate; and

the second predicted cost is based on the initial bid and the second predicted conversion rate and the first predicted cost is the same as the second predicted cost.

19. The system of claim 18, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises decreasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being less than the second predicted conversion rate.

20. The system of claim 18, wherein adjusting the initial bid for placement of the advertisement on the first publisher resource comprises increasing the initial bid for placement of the advertisement on the first publisher resource in response to the first predicted conversion rate being greater than the second predicted conversion rate.