PREDICTING CONTENT PERFORMANCE WITH INTEREST DATA

• US 20140068011A1
• Filed: 03/14/2013
• Published: 03/06/2014
• Est. Priority Date: 08/29/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ponnekanti, Shankar, Zamir, Oren Eli, Liu, Ting, Zhang, Xiaonan
• Granted Patent: US 9,549,017 B2
• Time in Patent Office: Days
• US Class Current: 709/219
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]
• CPC Class Codes: H04L 67/303 Terminal profiles
• CPC Class Codes: H04L 67/53 using third party service providers

Abstract

Systems and methods for predicting content performance with interest data include receiving a content selection request that includes a client identifier. One or more topical interest categories associated with the client identifier may be used as inputs to a prediction model to predict the likelihood of an online action occurring as a result of third-party content being selected. The predicted likelihood may be used to select third-party content.

Claims

1. A method of selecting content comprising:

receiving, at a processing circuit, a content selection request for third-party content to be presented by a client device in conjunction with first-party content, the content selection request including a client identifier;

retrieving data indicative of one or more topical interest categories associated with the client identifier;

identifying, by the processing circuit, one of the topical interest categories as an input for a prediction model;

selecting, by the processing circuit, a set of third-party content eligible for selection based in part on the one or more topical interest categories associated with the client identifier and based in part on a topic of the third-party content;

using the prediction model to predict a predicted action metric for the third-party content in the set, the predicted action metric corresponding to a predicted likelihood of an online action occurring as a result of the third-party content being selected;

selecting, by the processing circuit, third-party content from the set based in part on the predicted action metric associated with the third-party content; and

providing, by the processing circuit, an indication of the selected third-party content to be presented in conjunction with the first-party content.

2. The method of claim 1, wherein the set of third-party content eligible for selection is selected based in part on a match between a topic of the content in the set and a topic of the first-party content.

3. The method of claim 1, wherein the predicted action metric is a predicted click through rate.

4. The method of claim 1, wherein the predicted action metric is a predicted conversion rate.

5. The method of claim 1, wherein the prediction model comprises a logistic regression model.

6. The method of claim 5, wherein an input of the logistic regression model comprises a click propensity metric associated with the client identifier, the click propensity metric being indicative of how often the client identifier clicked on previously selected third-party content.

7. The method of claim 1, further comprising:

monitoring whether the predicted online action occurred; and

adjusting the prediction model based on the monitoring.

8. The method of claim 1, wherein the first-party content comprises an application executable by the client device.

9. The method of claim 5, wherein an input of the logistic regression model comprises a length of time the one or more topical categories have been associated with the client identifier.

10. The method of claim 1, wherein the indication comprises a command configured to cause the client device to retrieve the selected third-party content.

11. A system for selecting content comprising a processing circuit operable to:

receive a content selection request for third-party content to be presented by a client device in conjunction with first-party content, the content selection request including a client identifier;

retrieve data indicative of one or more topical interest categories associated with the client identifier;

identify one of the topical interest categories as an input for a prediction model;

select a set of third-party content eligible for selection based in part on the one or more topical interest categories associated with the client identifier and based in part on a topic of the third-party content;

use the prediction model to predict a predicted action metric for the third-party content in the set, the predicted action metric corresponding to a predicted likelihood of an online action occurring as a result of the third-party content being selected;

select third-party content from the set based in part on the predicted action metric associated with the third-party content; and

provide an indication of the selected third-party content to be presented in conjunction with the first-party content.

12. The system of claim 11, wherein the set of third-party content eligible for selection is selected based in part on a match between a topic of the content in the set and a topic of the first-party content.

13. The system of claim 11, wherein the predicted action metric is a predicted click through rate.

14. The system of claim 11, wherein the predicted action metric is a predicted conversion rate.

15. The system of claim 11, wherein the prediction model comprises a logistic regression model.

16. The system of claim 15, wherein an input of the logistic regression model comprises a click propensity metric associated with the client identifier, the click propensity metric being indicative of how often the client identifier clicked on previously selected third-party content.

17. The system of claim 11, wherein the processing circuit is further configured to monitor whether the predicted online action occurred and adjust the prediction model based on the monitoring.

18. The system of claim 11, wherein the first-party content comprises an application executable by the client device.

19. The system of claim 16, wherein an input of the logistic regression model comprises a length of time the one or more topical categories have been associated with the client identifier.

20. A computer-readable storage medium having machine instructions stored therein, the instructions being executable by a processor to cause the processor to perform operations comprising:

receiving a content selection request for third-party content to be presented by a client device in conjunction with first-party content, the content selection request including a client identifier;

retrieving data indicative of one or more topical interest categories associated with the client identifier;

identifying one of the topical interest categories as an input for a prediction model;

selecting a set of third-party content eligible for selection based in part on the one or more topical interest categories associated with the client identifier and based in part on a topic of the third-party content;

using the prediction model to predict a predicted action metric for the third-party content in the set, the predicted action metric corresponding to a predicted likelihood of an online action occurring as a result of the third-party content being selected;

selecting third-party content from the set based in part on the predicted action metric associated with the third-party content; and

providing an indication of the selected third-party content to be presented in conjunction with the first-party content.