Advertising model

1. A system, comprising:

one or more processors configured to:

determine (1) a demographic estimate, and (2) one or more quality measures associated with a user, wherein the demographic estimate comprises at least one of an estimated age and an estimated gender, wherein the demographic estimate is determined based at least in part on a set of observations associated with the user, the set of observations comprising at least one of a location, a time, a search term, click-through behavior, and information associated with an interest in a category, and wherein the one or more quality measures are determined based at least in part on one or more scores generated using one or more click filters, machine learning, and whether a need for the category has been met;

associate the at least one of the demographic estimate and the one or more quality measures with a user profile stored in a repository;

based at least in part on at least one of an HTML cookie, user agent information, geolocation information, a flash cookie, a cache cookie, and device identifier information, determine that an access to a site corresponds to the user profile;

receive, from an advertiser, a plurality of tiered bids, wherein a bid in the plurality of tiered bids comprises an amount the advertiser is willing to pay, wherein the plurality of tiered bids comprises (1) a first bid associated with a first demographic and a first quality level, and (2) a second bid associated with a second demographic and a second quality level, and wherein the first bid is different from the second bid; and

select the first bid based at least in part on (1) a match between the demographic estimate and the first demographic, and (2) a match between the first quality level and at least some of the one or more quality measures determined based at least in part on the one or more scores generated using the one or more click filters, machine learning, and whether the need for the category has been met; and

a memory coupled to the one or more processors and configured to provide the one or more processors with instructions.

2. The system of claim 1 wherein the one or more processors are further configured to perform persona detection based at least in part on one or more interactions with a device made by the user.

3. The system of claim 1 wherein the one or more processors are further configured to determine at least one of a discount and a surcharge associated with the selected bid based at least in part on the one or more quality measures.

4. The system of claim 1 wherein the one or more processors are further configured to update the user profile based at least in part on whether the user interacts with an advertisement.

5. The system of claim 1 wherein in response to the user clicking on an advertisement, a web browser of the user is directed to one of at least two distinct landing pages, wherein the directing is based at least in part on the one or more quality measures.

6. The system of claim 1 wherein the one or more processors are further configured to estimate a likelihood of conversion by using a click filter.

7. The system of claim 1 wherein the one more quality measures are further determined based at least in part on user context information comprising at least one of a time of day, an indication of a purchase, past activity associated with a keyword, a location of the user, and a webpage context.

8. The system of claim 1 wherein at least one bid in the plurality of tiered bids is based at least in part on a keyword.

9. The system of claim 1 wherein the one or more quality measures are further determined based at least in part on at least one of user account information, user context information, and general context information.

10. The system of claim 2 wherein performing the persona detection includes performing clustering.

11. A method, comprising:

determining (1) a demographic estimate, and (2) one or more quality measures associated with a user, wherein the demographic estimate comprises at least one of an estimated age and an estimated gender, wherein the demographic estimate is determined based at least in part on a set of observations associated with the user, the set of observations comprising at least one of a location, a time, a search term, click-through behavior, and information associated with an interest in a category, and wherein the one or more quality measures are determined based at least in part on one or more scores generated using one or more click filters, machine learning, and whether a need for the category has been met;

associating the demographic estimate and the one or more quality measures with a user profile stored in a repository;

based at least in part on at least one of an HTML cookie, user agent information, geolocation information, a flash cookie, a cache cookie, and device identifier information, determining that an access to a site corresponds to the user profile;

receiving, from an advertiser, a plurality of tiered bids, wherein a bid in the plurality of tiered bids comprises an amount the advertiser is willing to pay, wherein the plurality of tiered bids comprises ( 1 ) a first bid associated with a first demographic and a first quality level, and ( 2 ) a second bid associated with a second demographic and a second quality level, and wherein the first bid is different from the second bid; and

selecting the first bid based at least in part on (1) a match between the demographic estimate and the first demographic, and (2) a match between the first quality level and at least some of the one or more quality measures determined based at least in part on the one or more scores generated using the one or more click filters, machine learning, and whether the need for the category has been met.

12. The method of claim 11 further comprising performing persona detection based at least in part on one or more interactions with a device made by the user.

13. The method of claim 11 further comprising determining at least one of a discount and a surcharge associated with the selected bid based at least in part on the one or more quality measures.

14. The method of claim 11 further comprising updating the user profile based at least in part on whether the user interacts with an advertisement.

15. The method of claim 11 wherein in response to the user clicking on an advertisement, a web browser of the user is directed to one of at least two distinct landing pages, wherein the directing is based at least in part on the one or more quality measures.

16. The method of claim 11 further comprising estimating a likelihood of conversion by using a click filter.

17. The method of claim 11 wherein the one more quality measures are further determined based at least in part on user context information comprising at least one of a time of day, an indication of a purchase, past activity associated with a keyword, a location of the user, and a webpage context.

18. The method of claim 11 wherein at least one bid in the plurality of tiered bids is based at least in part on a keyword.

19. The method of claim 11 the one or more quality measures are further determined based at least in part on at least one of user account information, user context information, and general context information.

20. The method of claim 12 wherein performing the persona detection includes performing clustering.

21. A computer program product embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

determining (1) a demographic estimate, and (2) one or more quality measures associated with a user, wherein the demographic estimate comprises at least one of an estimated age and an estimated gender, wherein the demographic estimate is determined based at least in part on a set of observations associated with the user, the set of observations comprising at least one of a location, a time, a search term, click-through behavior, and information associated with an interest in a category, and wherein the one or more quality measures are determined based at least in part on one or more scores generated using one or more click filters, machine learning, and whether a need for the category has been met;

associating the demographic estimate and the one or more quality measures with a user profile stored in a repository;

based at least in part on at least one of an HTML cookie, user agent information, geolocation information, a flash cookie, a cache cookie, and device identifier information, determining that an access to a site corresponds to the user profile;

receiving, from an advertiser, a plurality of tiered bids, wherein a bid in the plurality of tiered bids comprises an amount the advertiser is willing to pay, wherein the plurality of tiered bids comprises (1) a first bid associated with a first demographic and a first quality level, and (2) a second bid associated with a second demographic and a second quality level, and wherein the first bid is different from the second bid; and

selecting the first bid based at least in part on (1) a match between the demographic estimate and the first demographic, and (2) a match between the first quality level and at least some of the one or more quality measures determined based at least in part on the one or more scores generated using the one or more click filters, machine learning, and whether the need for the category has been met.