Content-modification system with client-side advertisement caching
In one aspect, a method includes (i) identifying a plurality of upcoming content-modification opportunities for a content-presentation device, each respective content-modification opportunity corresponding to a respective underlying advertisement that is available for replacement by a respective supplemental advertisement; (ii) using the identified upcoming content-modification opportunities as a basis for determining expected values for a plurality of supplemental advertisements; (iii) selecting a subset of supplemental advertisements from among the plurality of supplemental advertisements based on the subset having expected values above a threshold value; (iv) in advance of the upcoming content-modification opportunities, sending the subset of supplemental advertisements to be locally stored at the content-presentation device; and (v) upon occurrence of one of the content-modification opportunities, causing the content-presentation device to replace one of the respective underlying advertisements with one of the locally stored supplemental advertisements.
1. A method, comprising:
determining, by a computing system, an expected value for supplemental content based at least in part on a probability of success of a content-modification operation upon occurrence of an upcoming content-modification opportunity using the supplemental content and based at least in part on an expected revenue gained from the content-modification operation using the supplemental content, wherein the expected revenue depends on an opportunity cost of an underlying content segment available for replacement by the supplemental content;
selecting, by the computing system, the supplemental content from among a plurality of supplemental content based on the supplemental content having the expected value above a threshold value to perform the content-modification operation that replaces the underlying content segment at a content-presentation device upon occurrence of the upcoming content-modification opportunity; and
sending, by the computing system, the supplemental content to the content-presentation device in advance of an upcoming content-modification opportunity of the content-presentation device.
2. The method of claim 1 , wherein determining the expected value for the supplemental content comprises determining the expected value based on one or more factors including (i) demographic information of an expected audience of the content-presentation device during the upcoming content-modification opportunity, (ii) a television channel expected to be presented by the content-presentation device during the upcoming content-modification opportunity, (iii) a number of available impressions for each supplemental content of the plurality of supplemental content, or (iv) creative separation or versioning rules for each supplemental content of the plurality of supplemental content.
3. The method of claim 2 , wherein determining the expected value for the supplemental content further comprises:
using the one or more factors as inputs for an artificial neural network; and
receiving, as an output from the artificial neural network, the expected value for the supplemental content.
4. The method of claim 3 , further comprising training, by the computing system, the artificial neural network based on actual revenues from content-modification operations performed in the past.
5. The method of claim 4 , further comprising repeatedly retraining the artificial neural network based on actual revenues from additional content-modification operations performed in the past.
6. The method of claim 1 , wherein the underlying content segment comprises an underlying advertisement, and wherein the expected revenue is based on a cost-per-mille of the underlying advertisement and the opportunity cost associated with performing the content-modification operation using the underlying advertisement.
7. The method of claim 1 , wherein the expected value is determined by multiplying the probability by the expected revenue.
8. A non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by at least one processor, cause performance of a set of operations comprising:
determining an expected value for supplemental content based at least in part on a probability of success of a content-modification operation upon occurrence of an upcoming content-modification opportunity using the supplemental content and based at least in part on an expected revenue gained from the content-modification operation using the supplemental content, wherein the expected revenue depends on an opportunity cost of an underlying content segment available for replacement by the supplemental content;
selecting the supplemental content from among a plurality of supplemental content based on the supplemental content having the expected value above a threshold value to perform the content-modification operation that replaces the underlying content segment at a content-presentation device upon occurrence of the upcoming content-modification opportunity; and
sending the supplemental content to the content-presentation device in advance of an upcoming content-modification opportunity of the content-presentation device.
9. The non-transitory computer-readable storage medium of claim 8 , wherein determining the expected value for the supplemental content comprises determining the expected value based on one or more factors including (i) demographic information of an expected audience of the content-presentation device during the upcoming content-modification opportunity, (ii) a television channel expected to be presented by the content-presentation device during the upcoming content-modification opportunity, (iii) a number of available impressions for each supplemental content of the plurality of supplemental content, or (iv) creative separation or versioning rules for each supplemental content of the plurality of supplemental content.
10. The non-transitory computer-readable storage medium of claim 9 , wherein determining the expected value for the supplemental content further comprises:
using the one or more factors as inputs for an artificial neural network; and
receiving, as an output from the artificial neural network, the expected value for the supplemental content.
11. The non-transitory computer-readable storage medium of claim 10 , the set of operations further comprising training the artificial neural network based on actual revenues from content-modification operations performed in the past.
12. The non-transitory computer-readable storage medium of claim 11 , the set of operations further comprising repeatedly retraining the artificial neural network based on actual revenues from additional content-modification operations performed in the past.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the underlying content segment comprises an underlying advertisement, and wherein the expected revenue is based on a cost-per-mille of the underlying advertisement and the opportunity cost associated with performing the content-modification operation using the underlying advertisement.
14. The non-transitory computer-readable storage medium of claim 8 , wherein the expected value is determined by multiplying the probability by the expected revenue.
15. A computing system comprising:
at least one processor; and
a non-transitory computer-readable storage medium, having stored thereon program instructions that, upon execution by the at least one processor, cause performance of a set of operations comprising:
determining an expected value for supplemental content based at least in part on a probability of success of a content-modification operation upon occurrence of an upcoming content-modification opportunity using the supplemental content and based at least in part on an expected revenue gained from the content-modification operation using the supplemental content, wherein the expected revenue depends on an opportunity cost of an underlying content segment available for replacement by the supplemental content;
selecting the supplemental content from among a plurality of supplemental content based on the supplemental content having the expected value above a threshold value to perform the content-modification operation that replaces the underlying content segment at a content-presentation device upon occurrence of the upcoming content-modification opportunity; and
sending the supplemental content to the content-presentation device in advance of an upcoming content-modification opportunity of the content-presentation device.
16. The computing system of claim 15 , wherein determining the expected value for the supplemental content comprises determining the expected value based on one or more factors including (i) demographic information of an expected audience of the content-presentation device during the upcoming content-modification opportunity, (ii) a television channel expected to be presented by the content-presentation device during the upcoming content-modification opportunity, (iii) a number of available impressions for each supplemental content of the plurality of supplemental content, or (iv) creative separation or versioning rules for each supplemental content of the plurality of supplemental content.
17. The computing system of claim 16 , wherein determining the expected value for the supplemental content further comprises:
using the one or more factors as inputs for an artificial neural network; and
receiving, as an output from the artificial neural network, the expected value for the supplemental content.
18. The computing system of claim 17 , the set of operations further comprising training, by the computing system, the artificial neural network based on actual revenues from content-modification operations performed in the past.
19. The computing system of claim 18 , the set of operations further comprising repeatedly retraining the artificial neural network based on actual revenues from additional content-modification operations performed in the past.
20. The computing system of claim 15 , wherein the underlying content segment comprises an underlying advertisement, and wherein the expected revenue is based on a cost-per-mille of the underlying advertisement and the opportunity cost associated with performing the content-modification operation using the underlying advertisement.