Expected activity of a user

1. A computer-implemented method comprising:

receiving a request for content from a user, the content to be displayed in a slot associated with an online resource;

determining, using one or more processors, an expected activity score for the user based at least in part on one or more criteria associated with a context of presenting the online resource to the user, wherein the expected activity score comprises a prediction of a rate at which the user will interact with content given a particular context, wherein determining the expected activity score for the user comprises:

retrieving, from an activity information database, data relating to a user's recent activity;

determining whether a threshold amount of data relating to the user's recent activity is available in the activity information database;

if less than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on users that are similar to the user; and

if more than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on the retrieved data relating to the user's recent activity, including:

determining the expected activity score based on previous interactions with content items in the context and impressions presented to the user in the context over a particular period of time; and

modifying the expected activity score by weighting more recent interactions higher than less recent interactions;

comparing the expected activity score for the user to a threshold;

selecting one or more content items to serve to the user based at least in part on the comparison; and

serving the selected content items to the user responsive to the request.

2. The method of claim 1 wherein the period of time is a recent time period, from a present point in time back a pre-defined amount of time in the past.

3. The method of claim 1 wherein the threshold corresponds to a recent expected activity score determined for the user, where the recent expected activity score is determined based on user interactions by the user in a recent time period and where the recent time period is shorter than the period of time.

4. The method of claim 1 wherein the threshold is a predetermined expected activity level.

5. The method of claim 1 wherein action-soliciting content includes click-to-convert content.

6. The method of claim 1 wherein non-action-soliciting content includes content items that have an information score that is higher than a predetermined threshold, the information score being a measure of whether a content item delivers information to the user rather than soliciting a direct response from the user.

7. The method of claim 1 wherein the criteria are selected from time of day, time of week, time of month, time of year, or location of the user.

8. The method of claim 1 wherein the criteria relate to subject matter associated with the online resource.

9. The method of claim 1 , wherein context includes one or more of subject matter related to the resource, the time of the request, or the location of the request.

10. The computer-implemented method of claim 1 , wherein action-soliciting content is served to the user responsive to the request when the expected activity score is at or above the threshold, and wherein non-action-soliciting content is served to the user responsive to the request when the expected activity score is below the threshold.

11. A computer program product tangibly embodied in a computer-readable storage device and comprising instructions that, when executed by a processor, cause the processor to:

receive a request for content from a user, the content to be displayed in a slot associated with an online resource;

determine an expected activity score for the user based at least in part on one or more criteria associated with a context of presenting the online resource to the user, wherein the expected activity score comprises a prediction of a rate at which the user will interact with content given a particular context, wherein determining the expected activity score for the user comprises:

retrieving, from an activity information database, data relating to a user's recent activity;

determining whether a threshold amount of data relating to the user's recent activity is available in the activity information database;

if less than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on users that are similar to the user; and

if more than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on the retrieved data relating to the user's recent activity, including:

determining the expected activity score based on previous interactions with content items in the context and impressions presented to the user in the context over a particular period of time; and

modifying the expected activity score by weighting more recent interactions higher than less recent interactions;

compare the expected activity score for the user to a threshold;

select one or more content items to serve to the user based at least in part on the comparison; and

serve the selected content items to the user responsive to the request.

12. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

receiving a request for content from a user, the content to be displayed in a slot associated with an online resource;

determining an expected activity score for the user based at least in part on one or more criteria associated with a context of presenting the online resource to the user, wherein the expected activity score comprises a prediction of a rate at which the user will interact with content given a particular context, wherein determining the expected activity score for the user comprises:

retrieving, from an activity information database, data relating to a user's recent activity;

determining whether a threshold amount of data relating to the user's recent activity is available in the activity information database;

if less than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on users that are similar to the user; and

if more than the threshold amount of data relating to the user's recent activity is available, determining the expected activity score for the user based on the retrieved data relating to the user's recent activity, including:

determining the expected activity score based on previous interactions with content items in the context and impressions presented to the user in the context over a particular period of time; and

modifying the expected activity score by weighting more recent interactions higher than less recent interactions;

comparing the expected activity score for the user to a threshold;

selecting one or more content items to serve to the user based at least in part on the comparison; and

serving the selected content items to the user responsive to the request.