DETERMINING CONVERSION PROBABILITY USING SESSION METRICS

• US 20100198772A1
• Filed: 08/04/2009
• Published: 08/05/2010
• Est. Priority Date: 02/05/2009
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Benson, Scott S., Sharma, Abhinay, Corduneanu, Adrian Dumitru, Silverman, Andrew E., Llinares, Tomas Lloret, Guha, Angshuman
• Granted Patent: US 8,346,709 B2
• Time in Patent Office: Days
• US Class Current: 706/52
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Methods, systems, and apparatus, including computer program products, for determining a probability that a traffic conversion of a content item associated with a content source (e.g., website) will occur based on past traffic patterns for that content source. A traffic conversion defines, for example, minimum traffic interactions of one or more associated user sessions with a content source. The minimum traffic interactions can be based on, for example, the duration of the one or more user sessions on the content source, or a quantity of pages associated with the content source navigated in the one or more associated user sessions.

Claims

1. A computer-implemented method, comprising:

defining a traffic conversion for a web property, wherein the traffic conversion defines a minimum traffic interaction of one or more associated user sessions with the web property;

identifying traffic conversion bid data for the web property;

receiving a request for a content item associated with the web property;

determining by one or more processing devices conversion probability data, the conversion probability data defining a conversion probability that the traffic conversion will occur subsequent to a selection of the content item; and

determining by the one or more processing devices bid data for the content item request based on the traffic conversion bid data and the conversion probability data.

2. The method of claim 1 wherein the traffic conversion defines the minimum traffic interaction based on a duration of the one or more user sessions on the web property.

3. The method of claim 1 wherein the traffic conversion defines the minimum traffic interaction based on a quantity of web pages associated with the web property navigated in the one or more user sessions.

4. The method of claim 1, further comprising:

providing the content item to be displayed to a client device;

determining whether the content item was selected at the client device; and

determining whether the traffic conversion occurred in the one or more user sessions.

5. The method of claim 4, further comprising:

if the content item was selected and the traffic conversion occurred, then debiting an account associated with the web property for an amount defined by the traffic conversion bid data.

6. The method of claim 5, further comprising:

if the content item was selected and the traffic conversion failed to occur, then logging but not debiting the account associated with the web property for the amount defined by the traffic conversion bid data.

7. The method of claim 1, further comprising:

providing the content item to be displayed to a client device;

determining whether the content item was selected at the client device; and

if the content item was selected, then debiting an account associated with the web property for an amount defined by the bid data.

8. The method of claim 1 wherein determining bid data for the content item comprises:

multiplying the conversion probability data for a given content item by the traffic conversion bid data.

9. The method of claim 1 wherein determining conversion probability data comprises:

analyzing traffic pattern data for the web property to identify traffic interaction levels of a plurality of past user sessions with the web property, the traffic pattern data defining traffic patterns for the plurality of past user sessions on the web property; and

defining durations of each of the plurality of past user sessions on the web property and a quantity of web pages associated with the web property navigated in each of the plurality of past user sessions.

10. The method of claim 9 wherein determining conversion probability data comprises:

comparing the minimum traffic interaction defined by the traffic conversion to the traffic interaction levels identified by the analyzed traffic pattern data; and

generating the conversion probability data based on the comparison.

11. The method of claim 9 wherein determining conversion probability data comprises:

utilizing a logistic regression model to determine the conversion probability data for a given content item based on the analyzed traffic pattern data.

12. The method of claim 1 wherein the content item is an advertisement.

13. A system, comprising:

a content item request module configured to identify a request for a content item associated with a web property;

a traffic conversion learning module configured to;

identify a traffic conversion for the web property, wherein the traffic conversion defines a minimum traffic interaction of one or more associated user sessions with the web property; and

determine conversion probability data, the conversion probability data defining a conversion probability that the traffic conversion will occur subsequent to a selection of the content item; and

a bid determining module configured to;

identify traffic conversion bid data for the web property; and

determine bid data for the content item request based on the traffic conversion bid data and the conversion probability data.

14. The system of claim 13 wherein the traffic conversion defines the minimum traffic interaction based on a duration of the one or more user sessions on the web property.

15. The system of claim 13 wherein traffic conversion defines the minimum traffic interaction based on a quantity of web pages associated with the web property navigated in the one or more user sessions.

16. The system of claim 13 wherein to determine the bid data for the content item request, the bid determining module is configured to multiply the conversion probability data by the traffic conversion bid data.

17. The system of claim 13 wherein the traffic conversion learning module is configured to:

analyze traffic pattern data for the web property to identify traffic interaction levels of a plurality of past user sessions on the web property, the traffic pattern data defining traffic patterns for the plurality of past user sessions on the web property;

define durations of each of the plurality of past user sessions on the web property; and

define a quantity of web pages associated with the web property navigated in each of the plurality of past user sessions.

18. The system of claim 17 wherein to determine the conversion probability data, the traffic conversion learning module is configured to:

compare the minimum traffic interaction defined by the traffic conversion to the traffic interaction levels identified by the analyzed traffic pattern data; and

generate the conversion probability data based on the comparison.

19. Software stored on a computer readable medium and comprising instructions executable by a processing device and upon such execution cause the processing device to perform operations comprising:

define a traffic conversion for a content source, wherein the traffic conversion defines a minimum traffic interaction of one or more associated user sessions with the content source;

identify traffic conversion bid data for the content source;

receive a request for a content item associated with the content source;

determine conversion probability data, the conversion probability data defining a conversion probability that the traffic conversion will occur subsequent to a selection of the content item; and

determine bid data for the content item request based on the traffic conversion bid data and the conversion probability data.

20. The software of claim 19 wherein the traffic conversion defines the minimum traffic interaction based on a duration of the one or more user sessions on the content source.

21. The software of claim 19 wherein the traffic conversion defines the minimum traffic interaction based on a quantity of web pages associated with the content source navigated in the one or more user sessions.

22. The software of claim 19 wherein the content item is an advertisement.