Provider-Specific Demographic Assignment Using Iterative Proportional Fitting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing household demographic assignment models fail to accurately account for demographic skews among return path data providers, leading to biased and inaccurate demographic assignments and audience measurement metrics.
Innovation Solution
A methodology using iterative proportional fitting to determine provider-specific demographic distribution targets, adjusting for regional demographic skews by leveraging higher panel samples and regional adjustments, and utilizing mixed integer programming for precise household demographic assignments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing household demographic assignment models are used, then demographic assignments can be made, but they fail to accurately account for demographic skews among return path data providers, leading to biased and inaccurate demographic assignments
Solution Approach 1:
The patent applies local quality by determining provider-specific demographic distribution targets for each television viewing area rather than using a single uniform demographic target. This allows the system to account for local demographic skews specific to each provider and region, thereby improving measurement precision while reducing bias in demographic assignments.
Solution Approach 2:
The patent changes the parameter approach by using iterative proportional fitting to calculate provider-specific demographic distribution targets based on local panel data and provider subscriber information. This dynamic parameter adjustment allows the system to adapt to varying demographic compositions across different providers and regions, resolving the contradiction between accuracy and reliability.
2Measurement precision
If provider-specific demographic distribution targets are determined using iterative proportional fitting, then accuracy of demographic assignments is improved, but computational complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the demographic assignment problem into smaller, manageable components - determining provider-specific targets for each television viewing area separately using iterative proportional fitting. This segmented approach, while computationally intensive for each segment, allows the overall system to maintain precision through localized optimization rather than attempting a monolithic solution.
Solution Approach 2:
The patent uses iterative proportional fitting as an intermediary computational method that bridges panel data and provider subscriber information to derive provider-specific demographic targets. This intermediary algorithm reconciles different data sources and constraints, enabling accurate demographic assignments while managing computational complexity through a systematic iterative process.
Data Source
AI summary
An example method includes determining a provider distribution by television viewing area using a provider-reported number of subscribers for a television viewing area and a sum of weights of panelist households that are located within the television viewing area. The method also includes obtaining a target distribution of a characteristic for the television viewing area. In addition, the method includes determining, using iterative proportional fitting, provider-specific distributions of the characteristic for the television viewing area. And the method includes using the provider-specific distributions of the characteristic for the television viewing area as a basis for assigning values of the characteristic to households that are subscribers of the return path data provider and located in the television viewing area.