Method and system for creating a predictive model for targeting webpage to a surfer

• US 8,799,200 B2
• Filed: 07/16/2009
• Issued: 08/05/2014
• Est. Priority Date: 07/25/2008
• Status: Active Grant

• Current Assignee: Amedesa, Ltd., LivePerson Incorporated
• Original Assignee: LivePerson Incorporated
• Inventors: Lahav, Shlomo
• Primary Examiner(s): Wong, Lut
• Application Number:
  US12/504,265
• Publication Number:
  US 20100023475A1
• Time in Patent Office: 1,846 Days
• Field of Search: 706/45, 705/14.49
• US Class Current: 706/45
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0251 Targeted advertisements

Abstract

A system and method for creating a predictive model to select an object from a group of objects that can be associated with a requested web page, wherein a configuration of the requested web page defines a subgroup of one or more selected objects from the group of objects. Exemplary embodiments of the present invention seek to provide novel solutions for determining which content object, taken from a group of content objects, will be best suited for presentation in association with a link on a web page that has been requested by a certain surfer. Each web page can include one or more links to be associated with content objects from the group.

For each content object presented over a requested web page, a predictive model with relevant predictive factors is processed such that the predicted objective, the probability of success for example, is calculated. A success is defined as a surfer responding to the presented content. For example, should a surfer select a relevant content object, the probability of the objects that can be presented is calculated. Subsequently, the objects with the highest predictive expected utility are selected to be associated with the links in the web page requested by the surfer.

Claims

1. A computer-implemented method, comprising:

receiving, by a computing device, a plurality of requests for a web page from a plurality of sources, wherein the web page includes a configuration defining one or more objects presented with the web page, wherein each object is associated with a separate predictive model including one or more predictive factors, wherein the one or more predictive factors are determined using the plurality of received requests, wherein the one or more predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected by any one of the plurality of sources when presented in the configuration of the web page;

retrieving predictive information related to the plurality of requests;

determining one or more predictive factors for an object presented with the web page, wherein the one or more predictive factors are determined using the retrieved predictive information;

dividing one or more of the predictive factors into one or more bins, wherein each bin includes a range of predictive factor values, wherein each bin is defined by a prediction efficiency of the range of predictive values within a bin, and wherein prediction efficiency relates to an ability to predict whether an object will be selected;

creating a bins table for the object, wherein the bins table includes the one or more bins;

generating a predictive model for the object using the bins table, wherein the generated predictive model is associated with the object;

receiving a subsequent request for the web page from a source, wherein the subsequent request is received after the plurality of requests, and wherein the subsequent request includes subsequent predictive information;

retrieving the predictive model associated with the object;

retrieving one or more predictive factors for the object, wherein the one or more predictive factors are associated with the subsequent predictive information;

determining a predictive value for the object using the generated predictive model, wherein the predictive value is determined by inputting the one or more retrieved predictive factors; and

selecting the object for inclusion in the configuration of the web page, wherein the object is selected using the predictive value.

2. The method of claim 1, wherein generating the predictive model includes performing logistic regression, linear regression, or decision tree analysis.

3. The method of claim 1, wherein the predictive information includes behavioral information and information associated with the request for the web page.

4. The method of claim 3, wherein the behavioral information includes a time of one or more previous visits in a domain that includes the requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, or a number of times that the object has been selected.

5. The method of claim 4, wherein the behavioral information is stored in a cookie.

6. The method of claim 3, wherein the information associated with the request for the web page includes a receipt time of the request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.

7. The method of claim 1, wherein the predictive model for the object is generated using a property set selected from a group of property sets, wherein the property set includes one or more parameters associated with the object.

8. The method of claim 7, further comprising:

generating a predictive model for each property set in the group of property sets to create a group of predictive models.

9. The method of claim 8, wherein the predictive model for the object is generated from the group of predictive models.

10. A system, comprising:

a processor; and

a non-transitory computer-readable storage medium containing instructions configured to cause the processor to perform operations including;

receiving a plurality of requests for a web page from a plurality of sources, wherein the web page includes a configuration defining one or more objects presented with the web page, wherein each object is associated with a separate predictive model including one or more predictive factors, wherein the one or more predictive factors are determined using the plurality of received requests, wherein the one or more predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected by any one of the plurality of sources when presented in the configuration of the web page;

retrieving predictive information related to the plurality of requests;

determining one or more predictive factors for an object presented with the web page, wherein the one or more predictive factors are determined using the retrieved predictive information;

dividing one or more of the predictive factors into one or more bins, wherein each bin includes a range of predictive factor values, wherein each bin is defined by a prediction efficiency of the range of predictive values within a bin, and wherein prediction efficiency relates to an ability to predict whether an object will be selected;

creating a bins table for the object, wherein the bins table includes the one or more bins;

generating a predictive model for the object using the bins table, wherein the generated predictive model is associated with the object;

receiving a subsequent request for the web page from a source, wherein the subsequent request is received after the plurality of requests, and wherein the subsequent request includes subsequent predictive information;

retrieving the predictive model associated with the object;

retrieving one or more predictive factors for the object, wherein the one or more predictive factors are associated with the subsequent predictive information;

determining a predictive value for the object using the generated predictive model, wherein the predictive value is determined by inputting the one or more retrieved predictive factors; and

selecting the object for inclusion in the configuration of the web page, wherein the object is selected using the predictive value.

11. The system of claim 10, wherein the predictive information includes behavioral information and information associated with the request for the web page.

12. The system of claim 11, wherein the behavioral information includes a time of one or more previous visits in a domain that includes the requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, or a number of times that the object has been selected.

13. The system of claim 12, wherein the behavioral information is stored in a cookie.

14. The system of claim 11, wherein the information associated with the request for the web page includes a receipt time of the request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.

15. A computer-program product, tangibly embodied in a non-transitory machine-readable medium, including instructions configured to cause a data processing apparatus to:

receive a plurality of requests for a web page from a plurality of sources, wherein the web page includes a configuration defining one or more objects presented with the web page, wherein each object is associated with a separate predictive model including one or more predictive factors, wherein the one or more predictive factors are determined using the plurality of received requests, wherein the one or more predictive factors are used to calculate a predictive value, and wherein a predictive value corresponds to a likelihood that an object will be selected by any one of the plurality of sources when presented in the configuration of the web page;

retrieve predictive information related to the plurality of requests;

determine one or more predictive factors for an object presented with the web page, wherein the one or more predictive factors are determined using the retrieved predictive information;

divide one or more of the predictive factors into one or more bins, wherein each bin includes a range of predictive factor values, wherein each bin is defined by a prediction efficiency of the range of predictive values within a bin, and wherein prediction efficiency relates to an ability to predict whether an object will be selected;

create a bins table for the object, wherein the bins table includes the one or more bins;

generate a predictive model for the object using the bins table, wherein the generated predictive model is associated with the object;

receive a subsequent request for the web page from a source, wherein the subsequent request is received after the plurality of requests, and wherein the subsequent request includes subsequent predictive information;

retrieve the predictive model associated with the object;

retrieve one or more predictive factors for the object, wherein the one or more predictive factors are associated with the subsequent predictive information;

determine a predictive value for the object using the generated predictive model, wherein the predictive value is determined by inputting the one or more retrieved predictive factors; and

select the object for inclusion in the configuration of the web page, wherein the object is selected using the predictive value.

16. The computer-program product of claim 15, wherein the predictive information includes behavioral information stored in a cookie and information associated with the request for the web page.

17. The computer-program product of claim 16, wherein the behavioral information includes a time of one or more previous visits in a domain that includes the requested web page, a time that the web page was last requested, a number of visits in the domain, a number of times that the object has been presented, or a number of times that the object has been selected, and wherein the information associated with the request for the web page includes a receipt time of the request, a uniform resource locator key associated with the request, an internet protocol address, or a type of browser application.