TV Ad Targeting via Identity Hashing and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advertising technologies face challenges in effectively targeting and delivering video advertisements across multiple media platforms due to fragmented viewing data, limited data models, and restrictions from privacy regulations, leading to inefficient ad placement and inability to accurately track viewer behavior across devices.
Innovation Solution
A system that utilizes deep learning methodologies and identity hashing to bridge the gap between online and offline video strategies by combining consumer data from various sources, allowing for targeted TV inventory purchasing based on online viewing behavior, while protecting user privacy through anonymous data handling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional panel-based data models are used for TV advertising targeting, then privacy regulations are complied with, but advertising targeting precision and viewer behavior tracking capability deteriorate
Solution Approach 1:
The system segments viewer data by device type (smartphone, tablet, PC, TV) and creates separate data models for each device category. This allows precise tracking of viewing habits across devices while maintaining manageable data complexity through organized segmentation rather than monolithic data handling.
Solution Approach 2:
The system adds a temporal dimension to data collection by tracking viewing habits over time periods (e.g., last 7 days, last 30 days). This enables dynamic targeting based on recent behavior patterns while maintaining compliance through aggregated statistical analysis rather than individual tracking.
2Productivity
If static spreadsheet-based data management is used for advertising inventory selection, then implementation simplicity is maintained, but selection efficiency and response speed to market trends deteriorate
Solution Approach 1:
The system implements automated real-time bidding algorithms that autonomously select and purchase advertising inventory based on current market conditions and target audience data. This self-service capability eliminates manual spreadsheet management while achieving superior selection efficiency and rapid response to market trends.
Solution Approach 2:
The system incorporates real-time feedback loops where advertising performance data is continuously collected, analyzed, and used to adjust bidding strategies and inventory selection. This closed-loop feedback mechanism enables dynamic optimization of advertising spend and rapid adaptation to market changes.
3Loss of information
If consumer data is collected across multiple devices and platforms, then comprehensive viewer behavior understanding is achieved, but data fragmentation and coordination complexity increase
Solution Approach 1:
The system merges data from multiple devices (smartphone, tablet, PC, TV) and platforms into unified viewer profiles by identifying common identifiers and correlating viewing behaviors across devices. This consolidation achieves comprehensive viewer behavior understanding while reducing data fragmentation through integrated data structures.
Solution Approach 2:
The system introduces an intermediary data processing layer that standardizes and harmonizes data from different sources before integration. This intermediary layer handles format conversion, identifier mapping, and data validation, thereby reducing coordination complexity while maintaining complete viewer behavior tracking.
4Speed
If real-time bidding algorithms are implemented for TV inventory purchase, then advertising delivery speed and market responsiveness are improved, but computational resource requirements and system complexity increase
Solution Approach 1:
The system performs preliminary calculations by pre-processing and storing aggregated viewer behavior statistics and advertising inventory characteristics in advance. During real-time bidding, these pre-computed data structures enable rapid query and decision-making without requiring intensive on-the-fly computations, thereby reducing real-time computational resource consumption.
Data Source
AI summary
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.