Content modification system with viewer behavior-based content delivery selection feature

1. A method implemented by a computing system, the method comprising:

receiving, by the computing system and from one or more presentation devices, fingerprint information that facilitates identifying content being presented by the one or more presentation devices;

identifying, based on the fingerprint information and by the computing system, advertisements being communicated to the one or more presentation devices;

determining, based on the fingerprint information and by the computing system, amounts of time identified advertisements are being presented via the one or more presentation devices;

storing, in a database, records that associate the identified advertisements with user profile information associated with users of the one or more presentation devices, and with the amounts of time the identified advertisements are being presented;

receiving, from a particular content presentation device associated with particular user profile information, a request for an advertisement;

for one or more of the advertisements specified in the records, determining, by the computing system and based on the particular user profile information, a probability of whether at least a threshold portion of a particular advertisement will be presented on the particular content presentation device, and a cost associated with presentation of the particular advertisement on the particular content presentation device, wherein the threshold portion corresponds to an amount of time at which fees associated with the presentation of the particular advertisement can be assessed, and wherein the threshold portion is different for different advertisements;

calculating, by the computing system, an expected revenue associated with presentation of the particular advertisement based on the probability and the cost; and

when the expected revenue exceeds a threshold revenue, communicating the particular advertisement to the particular content presentation device.

2. The method according to claim 1 , wherein determining the probability further comprises:

determining one or more of a previous amount of time the particular advertisement has been viewed on the particular content presentation device, or previous amounts of times advertisements of a same type as the particular advertisement have been viewed on the particular content presentation device.

3. The method according to claim 1 , wherein the particular advertisement corresponds to a replacement advertisement to replace an advertisement communicated in a transmission sequence from a content distribution system.

4. The method according to claim 1 , wherein after communicating the particular advertisement to the particular content presentation device, the method further comprises:

updating the database record associated with the particular advertisement to indicate that the particular advertisement was presented.

5. The method according to claim 1 , wherein the expected revenue is determined as:

Expected Revenue=(Placement Probability×Advertiser Spend)−Placement Cost,

wherein the Placement Probability corresponds to the probability of whether at least a threshold portion of a particular advertisement will be presented on a particular content presentation device, the Advertiser Spend corresponds to an amount an advertiser is willing to pay for placement of the particular advertisement, and the Placement Cost corresponds to the cost associated with presentation of the particular advertisement on the particular content presentation device.

6. The method according to claim 1 , wherein determining the cost associated with presentation of the particular advertisement comprises:

determining a file size associated with the particular advertisement and a geographic location of the particular content presentation device, wherein the cost increases with the file size and depends on an operating cost associated with a content server in a geographic region for serving the particular advertisement.

7. The method according to claim 1 , wherein the particular advertisement is one of a plurality of replacement advertisements, the method further comprising:

calculating an expected revenue associated with presentation of each of the replacement advertisements based on a corresponding probability and cost associated with each replacement advertisement; and

selecting a replacement advertisement having a highest expected revenue as the particular advertisement to communicate to the particular content presentation device.

8. A non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by a processor of a computing system, cause performance of a set of operations comprising:

receiving, by the computing system and from one or more presentation devices, fingerprint information that facilitates identifying content being presented by the one or more presentation devices;

identifying, based on the fingerprint information and by the computing system, advertisements being communicated to the one or more presentation devices;

determining, based on the fingerprint information and by the computing system, amounts of time identified advertisements are being presented via the one or more presentation devices;

storing, in a database, records that associate the identified advertisements with user profile information associated with users of the one or more presentation devices, and with the amounts of time the identified advertisements are being presented;

receiving, from a particular content presentation device associated with particular user profile information, a request for an advertisement;

for one or more of the advertisements specified in the records, determining, by the processor and based on the particular user profile information, a probability of whether at least a threshold portion of a particular advertisement will be presented on a particular content presentation device, and a cost associated with presentation of the particular advertisement on the particular content presentation device, wherein the threshold portion corresponds to an amount of time at which fees associated with the presentation of the particular advertisement can be assessed, and wherein the threshold portion is different for different advertisements;

calculating, by the processor, an expected revenue associated with presentation of the particular advertisement based on the probability and the cost; and

when the expected revenue exceeds a threshold revenue, communicating the particular advertisement to the particular content presentation device.

9. The non-transitory computer-readable storage medium according to claim 8 , wherein determining the probability further comprises:

determining one or more of a previous amount of time the particular advertisement has been viewed on the particular content presentation device, or previous amounts of times of advertisements of a same type as the particular advertisement have been viewed on the particular content presentation device.

10. The non-transitory computer-readable storage medium according to claim 8 , wherein the particular advertisement corresponds to a replacement advertisement to replace an advertisement communicated in a transmission sequence from a content distribution system.

11. The non-transitory computer-readable storage medium according to claim 8 , wherein after communicating the particular advertisement to the particular content presentation device, the operations comprise:

updating the database record associated with the particular advertisement to indicate that the particular advertisement was presented.

12. The non-transitory computer-readable storage medium according to claim 8 , wherein the expected revenue is determined according to the following equation:

Expected Revenue=(Placement Probability×Advertiser Spend)−Placement Cost,

wherein the Placement Probability corresponds to the probability of whether at least a threshold portion of a particular advertisement will be presented on a particular content presentation device, the Advertiser Spend corresponds to an amount an advertiser is willing to pay for placement of the particular advertisement, and the Placement Cost corresponds to the cost associated with presentation of the particular advertisement on the particular content presentation device.

13. The non-transitory computer-readable storage medium according to claim 8 , wherein determining the cost associated with presentation of the particular advertisement comprises:

determining a file size associated with the particular advertisement and a geographic location of the particular content presentation device, wherein the cost increases with the file size and depends on an operating cost associated with a content server in a geographic region for serving the particular advertisement.

14. The non-transitory computer-readable storage medium according to claim 8 , wherein the particular advertisement is one of a plurality of replacement advertisements, wherein the operations comprise:

calculating an expected revenue associated with presentation of each of the replacement advertisements based on a corresponding probability and cost associated with each replacement advertisement; and

selecting a replacement advertisement having a highest expected revenue as the particular advertisement to communicate to the particular content presentation device.

15. A computing system comprising:

a processor; and

a non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by the processor, cause performance of a set of operations comprising:

receiving, by the computing system and from one or more presentation devices, fingerprint information that facilitates identifying content being presented by the one or more presentation devices;

identifying, based on the fingerprint information and by the computing system, advertisements being communicated to the one or more presentation devices;

determining, based on the fingerprint information and by the computing system, amounts of time identified advertisements are being presented via the one or more presentation devices;

storing, in a database, records that associate the identified advertisements with user profile information associated with users of the one or more presentation devices, and with the amounts of time the identified advertisements are being presented;

receiving, from a particular content presentation device associated with particular user profile information, a request for an advertisement;

for one or more of the advertisements specified in the records, determining, by the processor and based on the particular user profile information, a probability of whether at least a threshold portion of a particular advertisement will be presented on the particular content presentation device, and a cost associated with presentation of the particular advertisement on the particular content presentation device, wherein the threshold portion corresponds to an amount of time at which fees associated with the presentation of the particular advertisement can be assessed, and wherein the threshold portion is different for different advertisements;

calculating, by the processor, an expected revenue associated with presentation of the particular advertisement based on the probability and the cost; and

when the expected revenue exceeds a threshold revenue, communicating the particular advertisement to the particular content presentation device.

16. The computing system according to claim 15 , wherein determining the probability further comprises:

determining one or more of a previous amount of time the particular advertisement has been viewed on the particular content presentation device, or previous amounts of times of advertisements of a same type as the particular advertisement have been viewed on the particular content presentation device.

17. The computing system according to claim 15 , wherein the particular advertisement corresponds to a replacement advertisement to replace an advertisement communicated in a transmission sequence from a content distribution system.

18. The computing system according to claim 15 , wherein after communicating the particular advertisement to the particular content presentation device, the operations comprise:

updating the database record associated with the particular advertisement to indicate that the particular advertisement was presented.

19. The computing system according to claim 15 , wherein the expected revenue is determined according to the following equation:

Expected Revenue=(Placement Probability×Advertiser Spend)−Placement Cost,

wherein the Placement Probability corresponds to the probability of whether at least a threshold portion of a particular advertisement will be presented on a particular content presentation device, the Advertiser Spend corresponds to an amount an advertiser is willing to pay for placement of the particular advertisement, and the Placement Cost corresponds to the cost associated with presentation of the particular advertisement on the particular content presentation device.

20. The computing system according to claim 15 , wherein determining the cost associated with presentation of the particular advertisement comprises:

determining a file size associated with the particular advertisement and a geographic location of the particular content presentation device, wherein the cost increases with the file size and depends on an operating cost associated with a content server in a geographic region for serving the particular advertisement.