Cross-Platform Overlap Modeling Using Multivariate Probit
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately determine overlap in reach and impressions across platforms like linear TV, OTT, and YouTube due to the lack of device-level identification data from YouTube, leading to an under-identified system of equations.
Innovation Solution
A computer-implemented method using a multivariate probit model to estimate overlap by combining reach statistics from platforms that identify devices with those that do not, through an aggregation server and overlap calculator, employing a multivariate probit model to calculate exposure proportions across multiple platforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques are used to track reach and impressions, then statistics can be obtained for platforms that identify devices (linear TV, OTT), but overlap determination fails for platforms that do not provide identification information (YouTube)
Solution Approach 1:
The patent introduces an intermediary identification mechanism (device identifiers, cookies, or other tracking technologies) that bridges the gap between platforms with and without native identification capabilities. This intermediary allows YouTube impressions to be linked to specific devices, enabling overlap calculation with linear TV and OTT platforms that have direct device identification.
Solution Approach 2:
The patent transforms the problem by changing the parameter of identification from platform-provided to universally applicable device-level identifiers. By shifting from relying on platform-specific identification (which YouTube lacks) to device-level identifiers (which can track across all platforms), the system enables cross-platform overlap measurement.
2Measurement precision
If device-level identification is implemented across all platforms, then accurate overlap determination is possible, but system complexity and data privacy requirements increase
Solution Approach 1:
The patent segments the identification system into two parts: platforms that natively provide device identification (linear TV, OTT) and platforms that require intermediary tracking (YouTube). This segmentation allows each platform to operate with its native capabilities while the intermediary handles cross-platform linking, reducing overall system complexity compared to forcing universal device identification on all platforms.
Solution Approach 2:
The intermediary identification layer acts as a mediator that simplifies the system architecture by handling the complexity of cross-platform tracking centrally, rather than requiring each platform to implement full device-level identification capabilities.
3Measurement precision
If device-level identification data is collected from all platforms, then overlap statistics can be calculated, but data privacy compliance becomes more challenging
Solution Approach 1:
The intermediary identification mechanism collects minimal necessary data (device identifiers rather than detailed user information) to enable cross-platform tracking. This intermediary layer processes data in a privacy-preserving manner, aggregating information at the device level without exposing individual user identities, thus reducing privacy risks while maintaining measurement accuracy.
Solution Approach 2:
The patent changes the data collection parameter from detailed user-level information to aggregated device-level identifiers. This parameter change reduces the privacy sensitivity of the data while maintaining sufficient information for calculating cross-platform reach and impression overlap.
Data Source
AI summary
A multivariate probit model is used to determine overlaps for reach and impressions for a plurality of different platforms.