User behavior models based on source domain
A method for tailoring content in a web page is provided. There is a relationship between the source domain a user comes from and the behavior pattern of a user on a website. To predict the behavior patterns of a particular user coming from a particular source domain, first a large dataset is compiled from user logs. Second, session analysis is performed on the dataset to identify sessions, session characteristics, page view categories, and source categories. Third, sessions are clustered and analyzed to determine how the behavior changes according to a source category. Fourth, a mapping between source categories and behavior patterns is generated. When a user requests a page view from a source domain, if the source domain is mapped to a source category, then a tailored version of the page view is presented to the user based on the mapping between source categories and behavior patterns.
1. A method comprising:
establishing a plurality of source categories, wherein the plurality of source categories includes a particular source category to which a plurality of source domains are mapped;
based on behavior, at a site at which users may engage in any of a plurality of behavior patterns, of users that visit the site from different source domains, establishing a mapping between source categories to which those source domains belong and behavior patterns;
in response to a user visiting the site, performing the steps of:
determining a source domain from which the user is visiting the site;
determining that the source domain is mapped to the particular source category;
based, at least in part, on the particular source category, selecting a behavior pattern, of the plurality of behavior patterns, in which the user is likely to engage; and
customizing the user's experience at the site based, at least in part, on the selected behavior pattern;
wherein the method is performed by one or more special-purpose computing devices.
2. The method of claim 1 , wherein prior to the user visiting the site:
obtaining a dataset based, at least in part, on one or more logs that indicate page views of pages from the site;
identifying a plurality of sessions that are reflected in the dataset;
generating a mapping from the source domain to the selected behavior pattern based, at least in part, on (a) a mapping from the source domain to the particular source category and (b) a mapping form the particular source category to the selected behavior pattern;
wherein the step of selecting the behavior pattern is based, at least in part, on the mapping from the source domain to the selected behavior pattern.
3. The method of claim 2 , wherein:
the mapping from the particular source category to the selected behavior pattern is based, at least in part, on:
the particular source category associated with a session-cluster, wherein the session-cluster comprises one or more sessions of the plurality of sessions; and
the selected behavior pattern associated with the session-cluster.
4. The method of claim 3 , wherein the particular source category is associated with the session-cluster based, at least in part, on (a) the session-cluster's contribution in the particular source category and (b) the session-cluster's contribution in the selected behavior pattern.
5. The method of claim 2 , wherein:
the indicated page views each comprise one or more fields; and
obtaining the dataset, comprises filtering the indicated page views based, at least in part, on contents of at least one of the one or more fields of each of the indicated page views.
6. The method of claim 2 , wherein the mapping from the source domain to the particular source category is established manually.
7. The method of claim 2 , further comprising:
assigning one or more of the indicated page views to a page view category based, at least in part, on layout of the indicated page views;
wherein the selected behavior pattern corresponds to the page view category.
8. The method of claim 3 , further comprising:
generating the session-cluster from one or more sessions of the plurality of sessions based, at least in part, on canopy clustering.
9. The method of claim 3 , further comprising:
generating the session-cluster from one or more sessions of the plurality of sessions based, at least in part, on K-means clustering.
10. The method of claim 3 , further comprising:
determining an entropy for the session-cluster; and
wherein the mapping from the particular source category to the selected behavior pattern is based, at least in part, on the entropy for the session-cluster being greater than a particular threshold.
11. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause the one or more computing devices to perform:
establishing a plurality of source categories, wherein the plurality of source categories includes a particular source category to which a plurality of source domains are mapped;
based on behavior, at a site at which users may engage in any of a plurality of behavior patterns, of users that visit the site from different source domains, establishing a mapping between source categories to which those source domains belong and behavior patterns;
in response to a user visiting the site, performing the steps of:
determining a source domain from which the user is visiting the site;
determining that the source domain is mapped to the particular source category;
based, at least in part, on the particular source category, selecting a behavior pattern, of the plurality of behavior patterns, in which the user is likely to engage; and
customizing the user's experience at the site based, at least in part, on the selected behavior pattern.
12. The non-transitory storage media of claim 11 , wherein the instructions further cause the one or more computing devices to perform the steps of, prior to the user visiting the site:
obtaining a dataset based, at least in part, on one or more logs that indicate page views of pages from the site;
identifying a plurality of sessions that are reflected in the dataset;
generating a mapping from the source domain to the selected behavior pattern based, at least in part, on (a) a mapping from the source domain to the particular source category and (b) a mapping form the particular source category to the selected behavior pattern;
wherein the step of selecting the behavior pattern is based, at least in part, on the mapping from the source domain to the selected behavior pattern.
13. The non-transitory storage media of claim 12 , wherein:
the mapping from the source category to the selected behavior pattern is based, at least in part, on:
the source category associated with a session-cluster, wherein the session-cluster comprises one or more sessions of the plurality of sessions; and
the selected behavior pattern associated with the session-cluster.
14. The non-transitory storage media of claim 13 , wherein the particular source category is associated with the session-cluster based, at least in part, on (a) the session-cluster's contribution in the particular source category and (b) the session-cluster's contribution in the selected behavior pattern.
15. The non-transitory storage media of claim 12 , wherein:
the indicated page views each comprise one or more fields; and
obtaining the dataset, comprises filtering the indicated page views based, at least in part, on contents of at least one of the one or more fields of each of the indicated page views.
16. The non-transitory storage media of claim 12 , wherein the mapping from the source domain to the particular source category is established manually.
17. The non-transitory storage media of claim 12 , wherein the instructions further cause the one or more computing devices to perform the steps of:
assigning one or more of the indicated page views to a page view category based, at least in part, on layout of the indicated page views;
wherein the selected behavior pattern corresponds to the page view category.
18. The non-transitory storage media of claim 13 , wherein the instructions further cause the one or more computing devices to perform the steps of:
generating the session-cluster from one or more sessions of the plurality of sessions based, at least in part, on canopy clustering.
19. The non-transitory storage media of claim 13 , wherein the instructions further cause the one or more computing devices to perform the steps of:
generating the session-cluster from one or more sessions of the plurality of sessions based, at least in part, on K-means clustering.
20. The non-transitory storage media of claim 13 , wherein the instructions further cause the one or more computing devices to perform the steps of:
determining an entropy for the session-cluster; and
wherein the mapping from the particular source category to the selected behavior pattern is based, at least in part, on the entropy for the session-cluster being greater than a particular threshold.