Multi-platform Overlap Estimation Using Panel Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current internet audience measurement methods face challenges in accurately counting unique visitors across different devices, as cookies can be deleted or dynamically assigned, and users may access content from multiple devices, leading to overcounting or undercounting of unique visitors.
Innovation Solution
A method involving a panel of users to collect data, using beacon-based approaches and census data to derive an overlap function that estimates the number of users accessing media content across multiple platforms, and applying this function to census data to correct for device overlap and improve measurement accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If cookies are used to track users across devices, then user identification is simplified, but accuracy deteriorates due to cookie deletion and dynamic assignment leading to overcounting or undercounting
Solution Approach 1:
The patent introduces panel data as an intermediary between raw census data and final overlap estimates. Panel data from a sampled group of users serves as a mediator to infer overlap patterns in the larger census population, enabling accurate multi-device overlap estimation without directly tracking individual users across devices through cookies
Solution Approach 2:
The patent creates a representative copy of the user population through the sampled panel. By measuring overlap patterns in this panel subset and applying them to the full census data, the system replicates the behavior of individual user tracking across the entire population without actually tracking individuals, thus maintaining accuracy while avoiding cookie-related problems
2Measurement precision
If census data from all users is collected directly, then measurement accuracy improves, but data collection complexity and resources increase significantly
Solution Approach 1:
The patent segments the user population into two distinct groups: a sampled panel of users whose detailed multi-device behavior is tracked, and the broader census population whose overlap is estimated through statistical inference. This segmentation allows complex measurements to be performed on a manageable subset and then scaled to the entire population
Solution Approach 2:
The patent performs complete overlap analysis on a partial sample of the population rather than attempting to track every user. By collecting comprehensive panel data from a representative subset and using it to model census-level overlap, the system achieves accurate measurements without the prohibitive complexity of universal tracking
Data Source
AI summary
Panel and census data representing accesses by sets of users with multiple types of media platforms to media content associated with multiple media entities is accessed. An overlap in the accessed panel data that represents users who have accessed media content associated with the media entity with more than one of the multiple types of media platforms is determined. Based on the accessed panel data, the determined overlap in the accessed panel data, and the accessed census data, an overlap function that estimates an overlap in the accessed census data is derived. The derived overlap function is applied to census data associated with a media entity to estimate an overlap in the census data associated with the media entity. The overlap in the census data represents users who have accessed media content associated with the media entity with more than one of the multiple types of media platforms.