TV Ad Targeting via Set-Top Box Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current TV advertising systems lack the ability to deliver targeted advertisements to specific households at scale and fail to determine if a purchase was influenced by a TV advertisement, due to limitations in data collection and feedback mechanisms.
Innovation Solution
A system and method for evaluating television media instances to target desired product buyers by receiving heterogeneous media data, generating media asset patterns, calculating advertisement effectiveness measures, and predicting advertisement effectiveness based on historical airings, while maintaining user privacy through indirect data usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If TV advertising uses traditional broadcast transmission, then high bandwidth and very high quality TV signal are achieved, but the ability to deliver targeted advertisements to specific households is lost
Solution Approach 1:
The patent segments the broadcast signal into multiple versions with different advertising content. Set-top boxes identify households matching target audience criteria and selectively present appropriate ad versions, enabling targeted advertising while maintaining traditional broadcast infrastructure and signal quality.
2Loss of information
If TV advertising uses Nielsen panel tracking, then advertisement viewing data is collected, but the scale is limited and the system is expensive to maintain
Solution Approach 1:
The patent utilizes set-top boxes already present in households to automatically collect advertising exposure data. These devices self-report viewing information to advertisers, eliminating the need for manual Nielsen panel operations and enabling scalable data collection across millions of households without proportionally increasing system complexity or cost.
3Quantity of substance
If TV advertising embeds ads in a single high definition video stream, then high bandwidth transmission is achieved, but the ability to deliver one-to-one advertisements to households is lost
Solution Approach 1:
The patent makes the advertising content dynamic by creating multiple video stream versions with different advertisements. The system dynamically selects which ad version to present to each household based on real-time audience matching, allowing flexible targeted delivery while maintaining efficient use of broadcast bandwidth through selective signal presentation.
Data Source
AI summary
Television is the largest advertising category in the United States with over 65 billion spent by advertisers per year. A variety of different targeting algorithms are compared, ranging from the traditional age-gender targeting methods employed based on Nielsen ratings, to new approaches that attempt to target high probability buyers using Set Top Box data. The performance of these different algorithms on a real television campaign is shown, and the advantages and limitations of each method are discussed. In contrast to other theoretical work, all methods presented herein are compatible with targeting the existing 115 million Television households in the United States and are implementable on current television delivery systems.