Targeting TV advertising slots based on consumer online behavior
Within an advertising buying platform, advertising buyers are able to direct advertising content to TV/OTT/VOD inventory that matches targeted market segments. The advertising buyers select from a list of available market segments, and the system pairs the market segments to an anonymous dataset of media consumers (using a database of hashed online IDs). The dataset of hashed online IDs is then mapped to external OEM IDs (such as from a Smart TV) via the functions of a hashed identity mapping method. This permits the advertiser to target advertising content to a population of TV viewers. Also described herein are methods of bidding on programmatic TV content.
1. A method for targeting a population of media viewers to which to deliver advertising content, the method comprising:
receiving viewer data for a first population of consumers, wherein the viewer data comprises a device identifier and a list of one or more media items that were played on a device associated with a first consumer;
de-identifying the device identifier for the device by creating a hash-ID for the device, the hash-ID being created based on the device identifier and the list of one or more media items that were played on the device;
associating the hash-ID for the device with a first hashed consumer identifier of the first consumer;
determining that the first hashed consumer identifier of the first consumer, and a second hashed consumer identifier of a second consumer are both connected to the device, the second consumer being in the first population of consumers;
identifying one or more slots of advertising inventory based on one or more demographic factors of consumers in the first population of consumers and the list of one or more media items associated with those consumers;
providing a mechanism for an advertiser to purchase a slot of advertising inventory relevant to the population of consumers; and
responsive to the advertiser purchasing the slot of advertising inventory, instructing a media conduit to deliver an item of advertising content to the device as an attempt to deliver the item of the advertising content to both the first consumer and the second consumer.
2. The method of claim 1 , wherein the viewer data comprises programmatic viewer data.
3. The method of claim 1 , wherein the purchasing comprises bidding on inventory including by real-time bidding, or by bidding on programmatic TV content.
4. The method of claim 1 , further comprising:
presenting, via a browser or web-enabled interface, a market segment selection form permitting an advertiser to select from a variety of market segment categories.
5. The method of claim 1 , wherein the consumer data comprises transmutable and non-transmutable data.
6. The method of claim 1 , further comprising:
predicting, via a machine learning process, inventory slots for market segments.
7. The method of claim 1 , wherein the de-identifying uses a one-way hash function.
8. The method of claim 1 , wherein the slot of advertising inventory that is purchased is delivered on a programmatic TV or on an analog TV.
9. The method of claim 1 , the first consumer and second consumer being related in a graph of consumer data, wherein a relationship of the first consumer and second consumer in the graph of consumer data being associated with a weight indicative of a degree of similarity of the first consumer and second consumer, the method including:
identifying a change to an online behavioral attribute associated with the second consumer; and
updating the weight, based on the change to the online behavioral attribute associated with the second consumer, to generate an updated weight indicative of the degree of similarity of an online behavioral data of the first consumer and the online behavioral data of the second consumer, wherein the updated weight is a numerical value that includes zero.
10. The method of claim 9 further comprising generating the weight indicative of the degree of similarity of the first consumer and the second consumer.
11. The method of claim 10 , wherein generating the weight indicative of the degree of similarity of the first consumer and the second consumer includes:
identifying a first attribute associated with the first consumer;
identifying a second attribute associated with the second consumer;
determining a similarity between the first attribute and the second attribute; and
generating the weight based on the similarity between the first attribute and the second attribute.
12. The method of claim 11 , wherein generating the weight further comprises:
generating a first intermediate weight based on the similarity between the first attribute and the second attribute;
identifying a third attribute associated with the first consumer;
identifying a fourth attribute associated with the second consumer;
generating a second intermediate weight based on the similarity between the third attribute and the fourth attribute; and
generating the weight based on the first intermediate weight and the second intermediate weight.
13. The method of claim 11 , wherein the updated weight is generated based on a change to at least one of the first attribute and the second attribute.
14. A system, comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions that are executable by the one or more processors to perform operations comprising:
receive viewer data for a first population of consumers, wherein the viewer data comprises at least one device identifier and a list of one or more media items that were played on a device associated with a first consumer;
de-identify the device identifier for the device by creating a hash-ID for the device, the hash-ID being created based on the device identifier and the list of one or more media items that were played on the device;
associate the hash-ID for the device with a first hashed consumer identifier of the first consumer determine that the first hashed consumer identifier of the first consumer, and a second hashed consumer identifier of a second consumer are both connected to the device, the second consumer being in the first population of consumers;
identify one or more slots of advertising inventory based on one or more demographic factors of consumers in the first population of consumers and the list of one or more media items associated with those consumers;
provide a mechanism for an advertiser to purchase a slot of advertising inventory relevant to the population of consumers; and
responsive to the advertiser purchasing the slot of advertising inventory, instruct a media conduit to deliver an item of advertising content to the device as an attempt to deliver the item of the advertising content to both the first consumer and the second consumer.
15. The system of claim 14 , the one or more processors further to generate a numerical weight indicative of a degree of similarity of the first consumer and the second consumer.
16. The system of claim 15 , wherein when generating the numerical weight indicative of the degree of similarity of the first consumer and the second consumer, the one or more processors further to:
identify first attribute associated with the first consumer;
identify a second attribute associated with the second consumer;
determine a similarity between the first attribute and the second attribute; and
generate the numerical weight based on the similarity between the first attribute and the second attribute.
17. The system of claim 16 , wherein an updated weight is generated based on a change to at least one of the first attribute and the second attribute.
18. A non-transitory computer-readable media storing instructions that are executable by one or more processors to perform operations comprising:
receive viewer data for a first population of consumers, wherein the viewer data comprises at least one device identifier and a list of one or more media items that were played on a device associated with a first consumer;
de-identify the device identifier for the device by creating a hash-ID for the device, the hash-ID being created based on the device identifier and the list of one or more media items that were played on the device;
associate the hash-ID for the device with a first hashed consumer identifier of the first consumer;
determine that the first hashed consumer identifier of the first consumer, and a second hashed consumer identifier of a second consumer are both connected to the device, the second consumer being in the first population of consumers;
identify one or more slots of advertising inventory based on one or more demographic factors of consumers in the first population of consumers and the list of one or more media items associated with those consumers;
provide a mechanism for an advertiser to purchase a slot of advertising inventory relevant to the population of consumers; and
responsive to the advertiser purchasing the slot of advertising inventory, instruct a media conduit to deliver an item of advertising content to the device as an attempt to deliver the item of the advertising content to both the first consumer and the second consumer.
19. The non-transitory computer-readable media of claim 18 , the instructions to cause the one or more processors further to generate a numerical weight indicative of a degree of similarity of the first consumer and the second consumer.
20. The non-transitory computer-readable media of claim 19 , wherein a updated weight is generated based on a change to at least one of the first attribute and the second attribute.