Yield optimization of cross-screen advertising placement
The current invention relates to a computer-generated method for optimizing placement of advertising content across multiple different devices. The system permits targeting of advertising content to consumers on TV and mobile devices that can be operated from within a multi-channel video programming distributor's environment. The system is able to use hard and soft constraints to come up with a number of possible targets for an advertising campaign and can then provide tools for optimizing those targets. 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 a user can adjust various constraints and optimize a distributor's revenue yield from advertising.
1. A method, comprising:
receiving first viewership data associated with a first consumer view of an advertisement of an advertising campaign, wherein the first consumer view of the advertisement includes a first view of a first portion of the advertisement on a first device and a second view of a second portion of the advertisement on a second device;
generating a first consumer classification based on the first viewership data;
calculating a predictive model of consumer behavior in view of the first consumer classification and a plurality of soft constraints, including running a first plurality of simulations using the predictive model in a plurality of advertisement campaigns, wherein running the first plurality of simulations includes determining a constraint satisfaction solution relative to a particular advertising campaign, and adjusting at least one soft constraint of the plurality of soft constraints in response to a user input;
receiving second viewership data associated with a second consumer view of the advertisement of the advertising campaign;
generating a second consumer classification based on the second viewership data;
updating the predictive model in view of the second consumer classification and in view of running a second plurality of simulations using the second consumer classification or second viewership data;
calculating an accuracy of the predictive model;
calculating lift data of the advertising campaign;
comparing the lift data to the predictive model;
updating the predictive model in view of the compared lift data and the calculated accuracy of the predictive model; and
sending the results of at least one of the first consumer classification, the second consumer classification, the predictive model, or the lift data, to a user interface.
2. The method of claim 1 , wherein at least the first consumer classification is a multi-dimensional consumer classification, and where at least one dimension of the first consumer classification is associated with a device on which the advertisement was viewed.
3. The method of claim 2 , wherein the multi-dimensional consumer classification includes linked data from each dimension of the first consumer classification, wherein each dimension represents a different device the first consumer used to view the advertisement.
4. The method of claim 2 , wherein the device of the first consumer includes at least one of a TV, a personal computer, or a mobile device.
5. The method of claim 1 , wherein the first consumer and the second consumer are a subset of a total audience of the advertising campaign.
6. The method of claim 1 , wherein the predictive model is updated by calculating a difference between the predictive model of consumer behavior and actual consumer behavior, using a feedback loop including an input of at least the first viewership data, the second viewership data, or a third viewership data, and generating an output of at least an updated predictive model of consumer behavior.
7. The method of claim 6 , wherein the predictive model is updated in real-time.
8. The method of claim 1 , further comprising deduplicating the first viewership data of the first consumer in response to the first consumer viewing the first portion of the advertisement on the first device and viewing the second portion of the advertisement on the second device.
9. The method of claim 8 , wherein the first portion of the advertisement includes a segment of the advertisement that comprises less than a full length of a runtime of the advertisement or a subset of advertisements of a plurality of advertisements intended to be viewed by the first consumer in the advertising campaign.
10. The method of claim 1 , wherein the lift data includes at least one of brand lift data or sales lift data.
11. A system, comprising:
at least one computer-readable media configured to store instructions; and
at least one processor coupled to the computer-readable media, the at least one processor configured to execute the instruction to cause the processor to perform operations, the operations comprising:
receive first viewership data associated with a first consumer view of an advertisement of an advertising campaign, wherein the first consumer view of the advertisement includes a first view of a first portion of the advertisement on a first device and a second view of a second portion of the advertisement on a second device;
generate a first multi-dimensional consumer classification based on the first viewership data, the first multi-dimensional consumer classification including at least one dimension associated with a device on which the advertisement was viewed;
calculate a predictive model of consumer behavior in view of the first consumer classification, the first consumer classification being within a particular audience segment;
receive second viewership data associated with a second consumer view of the advertisement of the advertising campaign;
generate a second consumer classification based on the second viewership data, the second consumer classification being within the particular audience segment;
update the predictive model in view of the second consumer classification;
determine, in view of a plurality of soft constraints, a particular configuration of the plurality of soft constraints to satisfy a constraint satisfaction relative to the advertisement campaign, the particular solution including an adjustment to at least on soft constraint of the plurality of soft constraints in response to a user input;
calculate an accuracy of the predictive model in view of the particular configuration of the plurality of soft constraints;
calculate lift data of the advertising campaign;
compare the lift data to the predictive model;
update the predictive model in view of the compared lift data and the calculated accuracy of the predictive model; and
send the results of at least one of the first consumer classification, the second consumer classification, the predictive model, the particular audience segment, or the lift data, to a user interface.
12. The system of claim 11 , wherein the multi-dimensional consumer classification includes linked data from each dimension of the first consumer classification, wherein each dimension represents a different device the first consumer used to view the advertisement.
13. The system of claim 11 , wherein the device of the first consumer includes at least one of a TV, a personal computer, or a mobile device.
14. The system of claim 11 , wherein the first consumer and the second consumer are a subset of a total audience of the advertising campaign.
15. The system of claim 11 , wherein the predictive model is updated by calculating a difference between the predictive model of consumer behavior and actual consumer behavior, using a feedback loop including an input of at least the first viewership data, the second viewership data, or a third viewership data, and generating an output of at least an updated predictive model of consumer behavior.
16. The system of claim 15 , wherein the predictive model is updated in real-time.
17. The system of claim 11 , further comprising deduplicate the first viewership data of the first consumer in response to the first consumer viewing the first portion of the advertisement on first device and viewing the second portion of the advertisement on the second device.
18. The system of claim 17 , wherein the first portion of the advertisement includes a segment of the advertisement that comprises less than a full length of a runtime of the advertisement or a subset of advertisements of a plurality of advertisements intended to be viewed by the first consumer in the advertising campaign.
19. The system of claim 11 , wherein the lift data includes at least one of brand lift data or sales lift data.
20. A non-transitory computer readable medium having stored therein executable code that, when executed by a processor, cause the processor to perform operations comprising:
receiving first viewership data associated with a first consumer view of an advertisement of an advertising campaign, the advertising campaign having a plurality of soft constraints, wherein the first consumer view of the advertisement includes a first view of a first portion of the advertisement on a first device and a second view of a second portion of the advertisement on a second device;
deduplicating the first viewership data of the first consumer in response to the first consumer viewing a first portion of the advertisement on a first device and viewing a second portion of the advertisement on a second device;
generating a first consumer classification based on the deduplicated first viewership data;
adjusting, in response to a user input, at least one of the plurality of soft constraints to satisfy a constraint satisfaction relative to the advertising campaign;
calculating a predictive model of consumer behavior in view of the first consumer classification and in view of an adjustment to the at least one of the plurality of soft constraints;
receiving second viewership data associated with a second consumer view of the advertisement of the advertising campaign;
deduplicating the second viewership data of the second consumer in response to the second consumer viewing the first portion of the advertisement on a third device and viewing a second portion of the advertisement on a fourth device;
generating a second consumer classification based on the deduplicated second viewership data;
updating the predictive model in view of the second consumer classification;
calculating an accuracy of the predictive model;
calculating lift data of the advertising campaign;
comparing the lift data to the predictive model;
updating the predictive model in view of the compared lift data and the calculated accuracy of the predictive model;
generating an incremental reach after running the advertising campaign; and
sending the results of at least one of the first consumer classification, the second consumer classification, the predictive model, the incremental reach, or the lift data, to a user interface.