Web page server process using visitor context and page features to select optimized web pages for display
View Patent ↗Embodiments of a web page optimization system are described. The system utilizes an accumulated body of visitor data regarding interaction with one or more web pages to determine an optimized web page to display to a visitor. Various types of session data, including network traffic data for the client computer, demographic information about the visitor, and general and specific session data of other visitors in similar browsing sessions are defined and compiled. Continuous full-path optimization from initial visitor interaction with the web page is provided through a visitor context analysis component that analyzes certain parameters related to how the visitor has accessed the web page. A real-time web page optimizer component introduces variations in one or more features of a web page to create a new web page, conducts structured tests of the new web page, compares the performance of the web page with one or more known served web pages and removes from presentation eligibility those pages with inferior performance. This facilitates real-time decision making of which web page to serve to a visitor based on an accumulated visitor context. It further allows the authoring of web pages that are optimized with respect to eliciting a desired user interaction with the web page.
1. A method comprising:
receiving, by one or more computer systems, a request for a landing page to be presented to a current visitor, the landing page having one or more landing-page components each of which has one or more possible feature variations, the landing page having a plurality of possible instances each of which results from combining different ones of the possible feature variations of the landing-page components;
accessing, by the one or more computer systems, a current visitor context of the current visitor, the current visitor context having one or more data associated with or concerning the current visitor;
predicting, by the one or more computer systems, a plurality of responses of the current visitor to the possible instances of the landing page based on the current visitor context, the possible feature variations of the possible instances of the landing page, one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the landing page have been presented, each of the previous actual instances of the landing page having been constructed for one of the previous visitors based on one of the possible instances of the landing page selected for the one of the previous visitors, and one or more actual responses of the previous visitors to the previous actual instances of the landing page;
selecting, by the one or more computer systems, one of the possible instances of the landing page for the current visitor based at least on the predicted responses;
constructing, by the one or more computer systems, a current actual instance of the landing page based on the selected one of the possible instances of the landing page; and
transmitting, by the one or more computer systems, the current actual instance of the landing page to the current visitor.
2. The method of claim 1 , wherein selecting one of the possible instances of the landing page for the current visitor is further based on one or more business rules predetermined for the current visitor context of the current visitor, the business rules governing whether particular ones of the possible feature variations may be presented to the current visitor.
3. The method of claim 1 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a predicted response that satisfies a threshold requirement.
4. The method of claim 3 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page.
5. The method of claim 1 , wherein:
the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used to test a response from the current visitor; and
the method further comprises:
receiving, by the one or more computer systems, an actual response of the current visitor to the current actual instance of the landing page constructed based on the possible instance of the landing page used to test the response from the current visitor; and
analyzing, by the one or more computer systems, the actual response of the current visitor.
6. The method of claim 1 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used as a control instance of the landing page for analyzing an actual response of the current visitor to the current actual instance of the landing page.
7. The method of claim 6 , further comprising:
receiving, by the one or more computer systems, an actual response of the current visitor to the current actual instance of the landing page constructed based on the control instance of the landing page; and
comparing, by the one or more computer systems, the actual response of the current visitor to the current actual instance of the landing page with at least one of the actual responses of at least one of the previous visitors to at least one of the previous actual instances of the landing page, the at least one of the previous actual instances of the landing page having been constructed based on at least one of the possible instances of the landing page selected for the at least one of the previous visitors such that the at least one of the possible instances of the landing page each has a predicted response that satisfies a threshold requirement.
8. The method of claim 1 , further comprising:
designating, by the one or more computer systems, one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page as a champion instance;
designating, by the one or more computer systems, one or more of the possible instances of the landing page that are different from the champion instance as one or more challenger instances, each of the challenger instances having been predicted as possibly being more desirable than the champion instance with respect to the current visitor context; and
selecting, by the one or more computer systems, the one of the possible instances of the landing page for the current visitor from the champion instance and the challenger instances.
9. The method of claim 1 , wherein the predicted responses of the current visitor to the possible instances of the landing page are determined using one or more statistical models that each has one or more inputs corresponding to the current visitor context, the possible feature variations of the possible instances of the landing page, the previous visitor contexts, the previous actual instances of the landing page, or the actual responses of the previous visitors to the previous actual instances of the landing page.
10. The method of claim 9 , wherein each of the statistical models is trained using the previous visitor contexts, the previous actual instances of the landing page, and the actual responses of the previous visitors to the previous actual instances of the landing page.
11. The method of claim 1 , wherein each of the predicted responses indicates a likelihood of a desired interaction between the current visitor and the corresponding possible instance of the landing page or a desired outcome from a possible interaction between the current visitor and the corresponding possible instance of the landing page.
12. The method of claim 11 , wherein each of the predicted responses indicates a likelihood of the current visitor purchasing one or more products through the corresponding possible instance of the landing page.
13. The method of claim 1 , wherein:
the landing-page components of the landing page comprise one or more of:
one or more layout components;
one or more color components;
one or more audio components;
one or more graphic components;
one or more video components; or
one or more text components, and
the possible feature variations of the landing-page components comprises one or more of:
one or more layout features;
one or more color features;
one or more audio features;
one or more graphic features;
one or more video features; or
one or more text features.
14. The method of claim 1 , wherein:
the current visitor context comprises one or more objective data or one or more behavioral data associated with or concerning the current visitor;
the objective data comprise one or more of:
one or more demographic data of the current visitor;
one or more background data of the current visitor;
one or more conditions of a web-browsing session associated with the current visitor;
one or more network-access data of the web-browsing session associated with the current visitor; or
one or more network-traffic data of the current web-browsing session associated with the current visitor, and
the behavioral data comprise one or more of:
one or more actions taken by the current visitor, one or more actual responses of the current visitor to the current actual instances of the landing page; or
a traffic source from which the current visitor accessed the current actual instances of the landing page.
15. The method of claim 1 , wherein:
each of the previous visitor contexts comprises one or more objective data or one or more behavioral data associated with or concerning one of the previous visitors;
the objective data of each of the previous visitor contexts comprise one or more of:
one or more demographic data of the corresponding previous visitor;
one or more background data of the corresponding previous visitor;
one or more conditions of a web-browsing session associated with the corresponding previous visitor;
one or more network-access data of the web-browsing session associated with the corresponding previous visitor; or
one or more network-traffic data of the web-browsing session associated with the corresponding previous visitor, and
the behavioral data of each of the previous visitor contexts comprise one or more of:
one or more actions taken by the corresponding previous visitor;
one or more actual responses of the corresponding previous visitor to one of the previous actual instances of the landing page; or
a traffic source from which the corresponding previous visitor accessed one of the previous actual instances of the landing page.
16. The method of claim 1 , further comprising:
receiving, by the one or more computer systems, an actual response of the current visitor to the current actual instance of the landing page; and
updating, by the one or more computer systems, the current visitor context based on the actual response of the current visitor to the current actual instance of the landing page.
17. One or more computer-readable storage media embodying software operable when executed by one or more computer systems to:
receive a request for a landing page to be presented to a current visitor, the landing page having one or more landing-page components each of which has one or more possible feature variations, the landing page having a plurality of possible instances each of which results from combining different ones of the possible feature variations of the landing-page components;
access a current visitor context of the current visitor, the current visitor context having one or more data associated with or concerning the current visitor;
predict a plurality of responses of the current visitor to the possible instances of the landing page based on the current visitor context, the possible feature variations of the possible instances of the landing page, one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the landing page have been presented, each of the previous actual instances of the landing page having been constructed for one of the previous visitors based on one of the possible instances of the landing page selected for the one of the previous visitors, and one or more actual responses of the previous visitors to the previous actual instances of the landing page;
select one of the possible instances of the landing page for the current visitor based at least on the predicted responses;
construct a current actual instance of the landing page based on the selected one of the possible instances of the landing page; and
transmit the current actual instance of the landing page to the current visitor.
18. The media of claim 17 , wherein to select one of the possible instances of the landing page for the current visitor is further based on one or more business rules predetermined for the current visitor context of the current visitor, the business rules governing whether particular ones of the possible feature variations may be presented to the current visitor.
19. The media of claim 17 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a predicted response that satisfies a threshold requirement.
20. The media of claim 19 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page.
21. The media of claim 17 , wherein:
the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used to test a response from the current visitor; and
the software is further operable when executed by the one or more computer systems to:
receive an actual response of the current visitor to the current actual instance of the landing page constructed based on the possible instance of the landing page used to test the response from the current visitor; and
analyze the actual response of the current visitor.
22. The media of claim 17 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used as a control instance of the landing page for analyzing an actual response of the current visitor to the current actual instance of the landing page.
23. The media of claim 22 , wherein the software is further operable when executed by the one or more computer systems to:
receive an actual response of the current visitor to the current actual instance of the landing page constructed based on the control instance of the landing page; and
compare the actual response of the current visitor to the current actual instance of the landing page with at least one of the actual responses of at least one of the previous visitors to at least one of the previous actual instances of the landing page, the at least one of the previous actual instances of the landing page having been constructed based on at least one of the possible instances of the landing page selected for the at least one of the previous visitors such that the at least one of the possible instances of the landing page each has a predicted response that satisfies a threshold requirement.
24. The media of claim 17 , wherein the software is further operable when executed by the one or more computer systems to:
designate one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page as a champion instance;
designate one or more of the possible instances of the landing page that are different from the champion instance as one or more challenger instances, each of the challenger instances having been predicted as possibly being more desirable than the champion instance with respect to the current visitor context; and
select the one of the possible instances of the landing page for the current visitor from the champion instance and the challenger instances.
25. The media of claim 17 , wherein the predicted responses of the current visitor to the possible instances of the landing page are determined using one or more statistical models that each have one or more inputs corresponding to the current visitor context, the possible feature variations of the possible instances of the landing page, the previous visitor contexts, the previous actual instances of the landing page, or the actual responses of the previous visitors to the previous actual instances of the landing page.
26. The media of claim 25 , wherein each of the statistical models is trained using the previous visitor contexts, the previous actual instances of the landing page, and the actual responses of the previous visitors to the previous actual instances of the landing page.
27. The media of claim 17 , wherein each of the predicted responses indicates a likelihood of a desired interaction between the current visitor and the corresponding possible instance of the landing page or a desired outcome from a possible interaction between the current visitor and the corresponding possible instance of the landing page.
28. The media of claim 27 , wherein each of the predicted responses indicates a likelihood of the current visitor purchasing one or more products through the corresponding possible instance of the landing page.
29. The media of claim 17 , wherein:
the landing-page components of the landing page comprise one or more of:
one or more layout components;
one or more color components;
one or more audio components;
one or more graphic components;
one or more video components; or
one or more text components, and
the possible feature variations of the landing-page components comprises one or more of:
one or more layout features;
one or more color features;
one or more audio features;
one or more graphic features;
one or more video features; or
one or more text features.
30. The media of claim 17 , wherein:
the current visitor context comprises one or more objective data or one or more behavioral data associated with or concerning the current visitor;
the objective data comprise one or more of:
one or more demographic data of the current visitor;
one or more background data of the current visitor;
one or more conditions of a web-browsing session associated with the current visitor;
one or more network-access data of the web-browsing session associated with the current visitor; or
one or more network-traffic data of the current web-browsing session associated with the current visitor, and
the behavioral data comprise one or more of:
one or more actions taken by the current visitor,
one or more actual responses of the current visitor to the current actual instances of the landing page; or
a traffic source from which the current visitor accessed the current actual instances of the landing page.
31. The media of claim 17 , wherein:
each of the previous visitor contexts comprises one or more objective data or one or more behavioral data associated with or concerning one of the previous visitors;
the objective data of each of the previous visitor contexts comprise one or more of:
one or more demographic data of the corresponding previous visitor;
one or more background data of the corresponding previous visitor;
one or more conditions of a web-browsing session associated with the corresponding previous visitor;
one or more network-access data of the web-browsing session associated with the corresponding previous visitor; or
one or more network-traffic data of the web-browsing session associated with the corresponding previous visitor, and
the behavioral data of each of the previous visitor contexts comprise one or more of:
one or more actions taken by the corresponding previous visitor;
one or more actual responses of the corresponding previous visitor to one of the previous actual instances of the landing page; or
a traffic source from which the corresponding previous visitor accessed one of the previous actual instances of the landing page.
32. The media of claim 17 , wherein the software is further operable when executed by the one or more computer systems to:
receive an actual response of the current visitor to the current actual instance of the landing page; and
update the current visitor context based on the actual response of the current visitor to the current actual instance of the landing page.
33. An apparatus comprising:
a memory comprising instructions executable by one or more processors; and
one or more processors coupled to the memory and operable to execute the instructions, the one or more processors being operable when executing the instructions to:
receive a request for a landing page to be presented to a current visitor, the landing page having one or more landing-page components each of which has one or more possible feature variations, the landing page having a plurality of possible instances each of which results from combining different ones of the possible feature variations of the landing-page components;
access a current visitor context of the current visitor, the current visitor context having one or more data associated with or concerning the current visitor;
predict a plurality of responses of the current visitor to the possible instances of the landing page based on the current visitor context, the possible feature variations of the possible instances of the landing page, one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the landing page have been presented, each of the previous actual instances of the landing page having been constructed for one of the previous visitors based on one of the possible instances of the landing page selected for the one of the previous visitors, and one or more actual responses of the previous visitors to the previous actual instances of the landing page;
select one of the possible instances of the landing page for the current visitor based at least on the predicted responses;
construct a current actual instance of the landing page based on the selected one of the possible instances of the landing page; and
transmit the current actual instance of the landing page to the current visitor.
34. The apparatus of claim 33 , wherein to select one of the possible instances of the landing page for the current visitor is further based on one or more business rules predetermined for the current visitor context of the current visitor, the business rules governing whether particular ones of the possible feature variations may be presented to the current visitor.
35. The apparatus of claim 33 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a predicted response that satisfies a threshold requirement.
36. The apparatus of claim 35 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page.
37. The apparatus of claim 33 , wherein:
the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used to test a response from the current visitor; and
the one or more processors are further operable when executing the instructions to:
receive an actual response of the current visitor to the current actual instance of the landing page constructed based on the possible instance of the landing page used to test the response from the current visitor; and
analyze the actual response of the current visitor.
38. The apparatus of claim 33 , wherein the selected one of the possible instances of the landing page for the current visitor is one of the possible instances of the landing page used as a control instance of the landing page for analyzing an actual response of the current visitor to the current actual instance of the landing page.
39. The apparatus of claim 38 , wherein the one or more processors are further operable when executing the instructions to:
receive an actual response of the current visitor to the current actual instance of the landing page constructed based on the control instance of the landing page; and
compare the actual response of the current visitor to the current actual instance of the landing page with at least one of the actual responses of at least one of the previous visitors to at least one of the previous actual instances of the landing page, the at least one of the previous actual instances of the landing page having been constructed based on at least one of the possible instances of the landing page selected for the at least one of the previous visitors such that the at least one of the possible instances of the landing page each has a predicted response that satisfies a threshold requirement.
40. The apparatus of claim 33 , wherein the one or more processors are further operable when executing the instructions to:
designate one of the possible instances of the landing page having a most desirable predicted response among all of the possible instances of the landing page as a champion instance;
designate one or more of the possible instances of the landing page that are different from the champion instance as one or more challenger instances, each of the challenger instances having been predicted as possibly being more desirable than the champion instance with respect to the current visitor context; and
select the one of the possible instances of the landing page for the current visitor from the champion instance and the challenger instances.
41. The apparatus of claim 33 , wherein the predicted responses of the current visitor to the possible instances of the landing page are determined using one or more statistical models that each has one or more inputs corresponding to the current visitor context, the possible feature variations of the possible instances of the landing page, the previous visitor contexts, the previous actual instances of the landing page, or the actual responses of the previous visitors to the previous actual instances of the landing page.
42. The apparatus of claim 41 , wherein each of the statistical models is trained using the previous visitor contexts, the previous actual instances of the landing page, and the actual responses of the previous visitors to the previous actual instances of the landing page.
43. The apparatus of claim 33 , wherein each of the predicted responses indicates a likelihood of a desired interaction between the current visitor and the corresponding possible instance of the landing page or a desired outcome from a possible interaction between the current visitor and the corresponding possible instance of the landing page.
44. The apparatus of claim 43 , wherein each of the predicted responses indicates a likelihood of the current visitor purchasing one or more products through the corresponding possible instance of the landing page.
45. The apparatus of claim 33 , wherein:
the landing-page components of the landing page comprise one or more of:
one or more layout components;
one or more color components;
one or more audio components;
one or more graphic components;
one or more video components; or
one or more text components, and
the possible feature variations of the landing-page components comprises one or more of:
one or more layout features;
one or more color features;
one or more audio features;
one or more graphic features;
one or more video features; or
one or more text features.
46. The apparatus of claim 33 , wherein:
the current visitor context comprises one or more objective data or one or more behavioral data associated with or concerning the current visitor;
the objective data comprise one or more of:
one or more demographic data of the current visitor;
one or more background data of the current visitor;
one or more conditions of a web-browsing session associated with the current visitor;
one or more network-access data of the web-browsing session associated with the current visitor; or
one or more network-traffic data of the current web-browsing session associated with the current visitor, and
the behavioral data comprise one or more of:
one or more actions taken by the current visitor,
one or more actual responses of the current visitor to the current actual instances of the landing page; or
a traffic source from which the current visitor accessed the current actual instances of the landing page.
47. The apparatus of claim 33 , wherein:
each of the previous visitor contexts comprises one or more objective data or one or more behavioral data associated with or concerning one of the previous visitors,
the objective data of each of the previous visitor contexts comprise one or more of:
one or more demographic data of the corresponding previous visitor;
one or more background data of the corresponding previous visitor;
one or more conditions of a web-browsing session associated with the corresponding previous visitor;
one or more network-access data of the web-browsing session associated with the corresponding previous visitor; or
one or more network-traffic data of the web-browsing session associated with the corresponding previous visitor, and
the behavioral data of each of the previous visitor contexts comprise one or more of:
one or more actions taken by the corresponding previous visitor;
one or more actual responses of the corresponding previous visitor to one of the previous actual instances of the landing page; or
a traffic source from which the corresponding previous visitor accessed one of the previous actual instances of the landing page.
48. The apparatus of claim 33 , wherein the one or more processors are further operable when executing the instructions to:
receive an actual response of the current visitor to the current actual instance of the landing page; and
update the current visitor context based on the actual response of the current visitor to the current actual instance of the landing page.
49. A system comprising:
means for receiving a request for a landing page to be presented to a current visitor, the landing page having one or more landing-page components each of which has one or more possible feature variations, the landing page having a plurality of possible instances each of which results from combining different ones of the possible feature variations of the landing-page components;
means for accessing a current visitor context of the current visitor, the current visitor context having one or more data associated with or concerning the current visitor;
means for predicting a plurality of responses of the current visitor to the possible instances of the landing page based on the current visitor context, the possible feature variations of the possible instances of the landing page, one or more previous visitor contexts of one or more previous visitors to whom one or more previous actual instances of the landing page have been presented, each of the previous actual instances of the landing page having been constructed for one of the previous visitors based on one of the possible instances of the landing page selected for the one of the previous visitors, and one or more actual responses of the previous visitors to the previous actual instances of the landing page;
means for selecting one of the possible instances of the landing page for the current visitor based at least on the predicted responses;
means for constructing a current actual instance of the landing page based on the selected one of the possible instances of the landing page; and
means for transmitting the current actual instance of the landing page to the current visitor.