Programmatic TV advertising placement using cross-screen consumer data
The current invention relates to a computer-generated method for optimizing placement of advertising content to consumers' TV's using a programmatic TV bidding model. The system can allocate advertising campaigns and plans to various inventory types based on the probability of accurate consumer matching. Consumer matching can be achieved by generation of look-alike models in a consumer's device graph to predict future consumption behavior. The system includes an interface through which an advertiser can access relevant information about inventory and success of a given placement.
1. A method comprising:
receiving, by a processor, advertising campaign information from an advertiser, the advertising campaign information comprises a schedule for delivery of an item of programmatic TV advertising content across one or more televisions accessed by a consumer;
defining, by the processor, a pool of consumers based on a graph of consumer properties, the graph being based on cross-screen data for at least one consumer in the pool of consumers, the graph being constructed using a combination of deterministic relationship data, probabilistic viewership data, and an offline event, wherein the cross-screen data is used to define the pool of consumers to which the programmatic TV advertising content is to be targeted, wherein a first consumer in the pool of consumers is associated with a particular device, wherein a second consumer in the pool of consumers is associated with the particular device;
identifying a similarity between the first consumer and the second consumer based on a deep learning analysis of a particular item of media content, the similarity being something that the first consumer and the second consumer have in common beyond the subject matter of the particular item of media content;
receiving a list of inventory from one or more content providers, wherein the list of inventory comprises one or more TV slots;
identifying one or more advertising targets, wherein each of the one or more advertising targets comprises one or more TV slots that are to be delivered within TV content identified as likely to be viewed by the pool of consumers, consistent with one or more of the advertising campaign information and the similarity between the first consumer and the second consumer;
bidding on one or more of the TV slots in an advertising target; and
if the bidding results in a success or a hold, instructing a media conduit to deliver the item of programmatic TV advertising content within the one or more TV slots to the consumer.
2. The method of claim 1 , wherein the bidding includes calculating a probability that the bid price will have an outcome of a win or a hold.
3. The method of claim 1 , wherein the TV content identified as likely to be viewed by the pool of consumers is based on a key performance indicator selected from audience reach and direct response.
4. The method of claim 1 , further comprising placing a further bid if the first bidding is either a hold or a loss.
5. The method of claim 1 , wherein the advertising target includes a gross rating point.
6. The method of claim 1 , wherein the slot includes a programming time selected from: program, and daypart.
7. The method of claim 1 , wherein the slot includes a geographic indicator selected from: DMA, national, and zip-code.
8. The method of claim 2 wherein the probability is calculated as a Bayesian distribution.
9. A system, comprising:
a memory; and
one or more processors coupled to the memory, the one or more processors being configured to execute instructions to cause the system to perform operations comprising:
receive advertising campaign information from an advertiser, the advertising campaign information comprises a schedule for delivery of an item of programmatic TV advertising content across one or more televisions accessed by a consumer;
define a pool of consumers based on a graph of consumer properties, the graph being based on cross-screen data for at least one consumer in the pool of consumers, the graph being constructed using a combination of deterministic relationship data, probabilistic viewership_data, and an offline event, wherein a first consumer in the pool of consumers is associated with a particular device, wherein a second consumer in the pool of consumers is associated with the particular device, wherein the cross-screen data is used to define the pool of consumers to which the programmatic TV advertising content is to be targeted;
receive a list of inventory from one or more content providers, wherein the list of inventory comprises one or more TV slots;
identify a similarity between the first consumer and the second consumer based on a deep learning analysis of a particular item of media content, the similarity being something that the first consumer and the second consumer have in common beyond the subject matter of the particular item of media content;
identify one or more advertising targets, wherein each of the one or more advertising targets comprises one or more TV slots that are to be delivered within TV content identified as likely to be viewed by the pool of consumers, consistent with the advertising campaign information and based on the similarity between the first consumer and the second consumer;
bid on one or more of the TV slots in an advertising target; and
if the bidding results in a success or a hold, instruct a media conduit to deliver the item of programmatic TV advertising content within the one or more TV slots to the consumer.
10. The system of claim 9 , wherein the bidding includes calculating a probability that the bid price will have an outcome of a win or a hold.
11. The system of claim 9 , wherein the TV content identified as likely to be viewed by the pool of consumers is based on a key performance indicator selected from audience reach and direct response.
12. The system of claim 9 , the operations further comprising placing a further bid if the first bidding is either a hold or a loss.
13. The system of claim 9 , wherein the advertising target includes a gross rating point.
14. The system of claim 9 , wherein the slot includes a programming time selected from: program, and daypart.
15. A non-transitory computer-readable medium encoded with instructions for executing a method for targeting delivery of advertising content, the instructions including instructions for:
receiving advertising campaign information from an advertiser, wherein the advertising campaign information comprises a schedule for delivery of an item of programmatic TV advertising content across one or more televisions accessed by a consumer;
defining a pool of consumers based on a graph of consumer properties, the graph being based on cross-screen data for at least one consumer in the pool of consumers, the graph being constructed using a combination of deterministic relationship data, probabilistic viewership data, and an offline event, wherein the cross-screen data is used to define the pool of consumers to which the programmatic TV advertising content is to be targeted, wherein a first consumer in the pool of consumers is associated with a particular device, wherein a second consumer in the pool of consumers is associated with the particular device;
identifying a similarity between the first consumer and the second consumer based on a deep learning analysis of a particular item of media content, the similarity being something that the first consumer and the second consumer have in common beyond the subject matter of the particular item of media content;
receiving a list of inventory from one or more content providers, wherein the list of inventory comprises one or more TV slots;
identifying one or more advertising targets, wherein each of the one or more advertising targets comprises one or more TV slots that are to be delivered within TV content identified as likely to be viewed by the pool of consumers, consistent with the advertising campaign information and based on the similarity between the first consumer and the second consumer;
bidding on one or more of the TV slots in an advertising target; and
if the bidding results in a success or a hold, instructing a media conduit to deliver the item of programmatic TV advertising content within the one or more TV slots to the consumer.
16. The non-transitory computer-readable medium of claim 15 , wherein the bidding includes calculating a probability that the bid price will have an outcome of a win or a hold.
17. The non-transitory computer-readable medium of claim 15 , wherein the TV content identified as likely to be viewed by the pool of consumers is based on a key performance indicator selected from audience reach and direct response.
18. The non-transitory computer-readable medium of claim 15 , further comprising placing a further bid if the first bidding is either a hold or a loss.
19. The non-transitory computer-readable medium of claim 15 , wherein the advertising target includes a gross rating point.
20. The non-transitory computer-readable medium of claim 15 , wherein the slot includes a programming time selected from: program, and daypart.