Cross-screen measurement accuracy in advertising performance

• US 10,555,050 B2
• Filed: 07/25/2016
• Issued: 02/04/2020
• Est. Priority Date: 07/24/2015
• Status: Active Grant

• Current Assignee: Videoamp, Inc.
• Original Assignee: Videoamp, Inc.
• Inventors: Ray, Debajyoti, McCray, Ross, Gullo, David, Prasad, Jay
• Primary Examiner(s): Kumar, Pankaj
• Assistant Examiner(s): Boyd, Alexander
• Application Number:
  US15/219,268
• Publication Number:
  US 20170034593A1
• Time in Patent Office: 1,289 Days
• CPC Class Codes: G06Q 30/0242 Determining effectiveness of advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: H04N 21/252 Processing of multiple end-users' preferences to derive collaborative data
• CPC Class Codes: H04N 21/2543 Billing , e.g. for subscription services payment schemes, architectures or protocols G06Q20/00; e-commerce G06Q30/00; arrangements for billing for the use of broadcast information or broadcast-related information H04H60/21
• CPC Class Codes: H04N 21/25883 being end-user demographical data, e.g. age, family status or address arrangements for identifying locations of users in broadcast systems H04H60/52
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/2668 Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles information retrieval from the Internet by querying with filtering and personalisation G06F16/9535; arrangements for replacing or switching information during the broadcast H04H20/10; push services over packet-switching network H04L12/1859; adaptation of message content in packet-switching networks H04L51/063
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4667 Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02

Abstract

The present invention is directed to statistical methods for measuring cross-screen efficacy as it relates to advertising. The improved statistical methods provide the ability for advertisers and advertising agencies to predict the behaviors of consumers based on their aggregated cross-screen behavior. The system creates a new output that includes optimized user segments and classifications. A second part of the output is improved measurement and prediction of future consumer behaviors based on the processed multi-sided data on cross-screen behavior.

Claims

1. A method for quantifying efficacy of an advertising campaign, the method comprising:

identifying a target audience based on one or more demographic factors;

identifying a set of devices, each device in the set of devices having a respective set of attributes;

identifying, in the set of devices, two or more display devices that each have a similar respective set of attributes;

creating a node to include the two or more display devices;

inferring from the node that the two or more display devices belong to a consumer that is in the target audience based on the two or more display devices having similar behavior at different times;

associating the two or more display devices with the consumer;

for the consumer in the target audience, identifying the two or more display devices accessible to the consumer, wherein the two or more display devices comprise at least one TV and at least one mobile device;

monitoring delivery of advertising content to the consumer in the target audience, wherein the advertising content comprises video content that is scheduled for delivery on the two or more display devices associated with the consumer;

inferring whether the consumer viewed the advertising content based on identifying the at least one TV and at least one mobile device in a device graph and determining that the at least one TV and at least one mobile device played at least a portion of a show that is associated with a broadcast of the advertising content; and

using the inference in calculation of a deduplicated reach for the advertising campaign, wherein the calculation of the deduplicated reach includes determining a likelihood indicative of whether the consumer saw the same advertising content on more than one device, wherein the calculation of the deduplicated reach for the advertising campaign excludes at least one instance of the consumer likely seeing the advertising content.

2. The method of claim 1, wherein behavioral data is obtained from a method selected from:

deep learning, machine learning, and Bayesian methods.

3. The method of claim 1, wherein behavioral data comprises first party and third party data.

4. The method of claim 1, further comprising aggregating behaviors from the two or more display devices of the node are aggregated to a set of node attributes for the node.

5. The method of claim 1, wherein inferring from the node that the two or more display devices belong to the consumer that is in the target audience based on the two or more display devices having similar behavior at different times includes determining a probability that the two or more display devices belong to the consumer, wherein the two or more display devices are associated with the consumer when the probability that the two or more display devices belong to the consumer is above a threshold probability.

6. A method of reducing redundancy of delivery of advertising content, the method comprising:

identifying a target audience based on one or more demographic factors, wherein the target audience comprises consumers to whom an advertising campaign is directed;

identifying a set of devices, each device in the set of devices having a respective set of attributes;

identifying, in the set of devices, two or more display devices that each have a similar respective set of attributes;

creating a node to include the two or more display devices;

inferring from the node that the two or more display devices belong to a consumer that is in the target audience based on the two or more display devices having similar behavior at different times;

associating the two or more display devices with the consumer;

for the consumer in the target audience, identifying the two or more display devices accessible to the consumer, wherein the two or more display devices comprise at least one TV and at least one mobile device;

monitoring delivery of advertising content to the consumer in the target audience, wherein the advertising content comprises video content that is scheduled for delivery on the two or more display devices associated with the consumer;

inferring whether the consumer viewed the advertising content based on identifying the at least one TV and at least one mobile device in a device graph and determining that the at least one TV and at least one mobile device played at least a portion of a show that is associated with a broadcast of the advertising content; and

if it is inferred that the consumer viewed both a first item of advertising content and a second item of advertising content, adjusting one or more parameters of the advertising campaign in order to reduce redundancy of delivery of the advertising content to the consumer during subsequent trials of the campaign, wherein the parameters are selected from one or more of;

demographic factors of the target audience;

sources of advertising inventory;

time of day of delivery; and

region of delivery.

7. The method of claim 6, wherein the sources of advertising inventory include:

TV channel, online website, and video-on-demand.

8. The method of claim 6, wherein the adjusting one or more parameters of the advertising campaign includes stopping scheduling of the advertising content online to the consumer.

9. The method of claim 6, wherein behavioral data is obtained from a method selected from:

deep learning, machine learning, and Bayesian methods.

10. The method of claim 6, wherein behavioral data comprises first party and third party data.

11. The method of claim 6, wherein identifying the target audience comprises identifying consumers that have at least a threshold similarity to each other.

12. The method of claim 6, further comprising aggregating behaviors from the two or more display devices of the node are aggregated to a set of node attributes for the node.

13. The method of claim 6, wherein inferring from the node that the two or more display devices belong to the consumer that is in the target audience based on the two or more display devices having similar behavior at different times includes determining a probability that the two or more display devices belong to the consumer, wherein the two or more display devices are associated with the consumer when the probability that the two or more display devices belong to the consumer is above a threshold probability.

14. A non-transitory computer-readable storage device having embedded therein a set of instructions which, when executed by one or more processors of a computer, causes the computer to execute operations comprising:

identifying a target audience based on one or more demographic factors;

identifying a set of devices, each device in the set of devices having a respective set of attributes;

identifying, in the set of devices, two or more display devices that each have a similar respective set of attributes;

creating a node to include the two or more display devices;

inferring from the node that the two or more display devices belong to a consumer that is in the target audience based on the two or more display devices having similar behavior at different times;

associating the two or more display devices with the consumer;

for the consumer in the target audience, identifying the two or more display devices accessible to the consumer, wherein the two or more display devices comprise at least one TV and at least one mobile device;

monitoring delivery of advertising content to the consumer in the target audience, wherein the advertising content comprises video content that is scheduled for delivery on the two or more display devices associated with the consumer;

inferring whether the consumer viewed the advertising content based on identifying the at least one TV and at least one mobile device in a device graph and determining that the at least one TV and at least one mobile device played at least a portion of a show that is associated with a broadcast of the advertising content; and

using the inference in calculation of a deduplicated reach for an advertising campaign, wherein the calculation of the deduplicated reach includes determining a likelihood indicative of whether the consumer saw the same advertising content on more than one device, wherein the calculation of the deduplicated reach for the advertising campaign excludes at least one instance of the consumer likely seeing the advertising content.

15. The non-transitory computer-readable storage device of claim 14 the operations further comprising aggregating behaviors from the two or more display devices of the node are aggregated to a set of node attributes for the node.

16. The non-transitory computer-readable storage device of claim 14, wherein inferring from the node that the two or more display devices belong to the consumer that is in the target audience based on the two or more display devices having similar behavior at different times includes determining a probability that the two or more display devices belong to the consumer, wherein the two or more display devices are associated with the consumer when the probability that the two or more display devices belong to the consumer is above a threshold probability.

17. The non-transitory computer-readable storage device of claim 14, wherein behavioral data is obtained from a method selected from:

deep learning, machine learning, and Bayesian methods.

18. The non-transitory computer-readable storage device of claim 14, wherein behavioral data comprises first party and third party data.

19. The non-transitory computer-readable storage device of claim 14, identifying the target audience comprises identifying consumers that have at least a threshold similarity to each other.