Personalizing sponsored search advertising layout using user behavior history
Embodiments of the invention relate to methods of presenting personalized search results pages to users, and to search engine systems and servers configured to implement such methods. For example, a method of presenting such a page to a user of a search engine includes steps of computing an engagement index of the user based on the distribution in time of that user's interactions with the search engine then presenting, in response to a query by the user, a personalized search results page to the user.
1. A method comprising:
computing, by a computer, an engagement index of a user based on a distribution in time of the user's interactions with a search engine, the engagement index comprising at least a measured frequency of the user's visits to the search engine, a measured recency of the user's visits to the search engine, and a measured intensity of the user's activity at the search engine, the measured intensity is associated with a number of search engine page views by the user, wherein the engagement index equals the measured frequency multiplied by the measured intensity and divided by the measured recency; and
presenting, in response to a query by the user, a personalized search results page to the user when the engagement index of the user meets a threshold value, wherein the threshold value indicates that the user is sufficiently engaged with the website to perform personalization and wherein, the personalized search results page for presenting to the user a personalized advertisement layout comprising:
a search related content; and
at least one advertisement.
2. The method of claim 1 , where the threshold value is set based on a probability of clicking on an advertisement.
3. The method of claim 2 , wherein a probability of clicking on an advertisement is used to determine the at least one presented advertisement.
4. The method of claim 1 where the engagement index is additionally based on user interest data inferred from the distribution of the user's interactions with non-search properties.
5. The method of claim 4 , wherein the non-search properties include one of the following: autos, finance, and sports.
6. The method of claim 1 , wherein the threshold value is determined by a business constraint.
7. The method of claim 6 , wherein the business constraint comprises expected revenue.
8. The method of claim 7 , wherein the expected revenue is calculated by:
Expected (Revenue|Query, Ad)=Cost(Ad)*Probability (click on Ad|Query, Ad).
9. An apparatus comprising:
a processor;
a storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
computing logic executed by the processor for computing an engagement index of a user based on a distribution in time of the user's interactions with a search engine, the engagement index comprising at least a measured frequency of the user's visits to the search engine, a measured recency of the user's visits to the search engine, and a measured intensity of the user's activity at the search engine, the measured intensity is associated with a number of search engine page views by the user, wherein the engagement index equals the measured frequency multiplied by the measured intensity and divided by the measured recency; and
presenting logic executed by the processor for presenting, in response to a query by the user, a personalized search results page to the user when the engagement index of the user meets a threshold value, wherein the threshold value indicates that the user is sufficiently engaged with the website to perform personalization and wherein, the personalized search results page for presenting to the user a personalized advertisement layout comprising:
a search related content; and
at least one advertisement.
10. A non-transitory computer readable storage medium tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining code for:
computing an engagement index of a user based on a distribution in time of the user's interactions with a search engine, the engagement index comprising at least a measured frequency of the user's visits to the search engine, a measured recency of the user's visits to the search engine, and a measured intensity of the user's activity at the search engine, the measured intensity is associated with a number of search engine page views by the user, wherein the engagement index equals the measured frequency multiplied by the measured intensity and divided by the measured recency; and
presenting, in response to a query by the user, a personalized search results page to the user when the engagement index of the user meets a threshold value, wherein the threshold value indicates that the user is sufficiently engaged with the website to perform personalization and wherein, the personalized search results page for presenting to the user a personalized advertisement layout comprising:
a search related content; and
at least one advertisement.
11. The non-transitory computer readable storage medium of claim 10 , where the threshold value is set based on a probability of clicking on an advertisement.
12. The non-transitory computer readable storage medium of claim 11 , wherein a probability of clicking on an advertisement is used to determine the at least one presented advertisement.
13. The non-transitory computer readable storage medium of claim 10 , where the engagement index is additionally based on user interest data inferred from the distribution of the user's interactions with non-search properties.
14. The non-transitory computer readable storage medium of claim 13 , wherein the non-search properties include one of the following: autos, finance, and sports.
15. The computer program product of claim 10 , wherein the threshold value is determined by a business constraint.
16. The non-transitory computer readable storage medium of claim 15 , wherein the business constraint comprises an expected revenue.
17. The non-transitory computer readable storage medium of claim 16 , wherein the expected revenue is calculated by:
Expected (Revenue|Query, Ad)=Cost (Ad)*Probability (click on Ad|Query, Ad).
18. The non-transitory computer readable storage medium of claim 10 , wherein the personalized advertisement layout further comprises a plurality of advertisement regions, where the personalized advertisement layout comprises at least one advertisement in a first advertisement region and no advertisements in a second advertisement region.
19. The apparatus of claim 9 , wherein the personalized advertisement layout further comprises a plurality of advertisement regions, where the personalized advertisement layout comprises at least one advertisement in a first advertisement region and no advertisements in a second advertisement region.
20. The apparatus of claim 9 , where the threshold value is set based on a probability of clicking on an advertisement.
21. The method of claim 1 , wherein the personalized advertisement layout further comprises a plurality of advertisement regions, where the personalized advertisement layout comprises at least one advertisement in a first advertisement region and no advertisements in a second advertisement region.