Campaign Mapping for Total Audience Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current audience measurement methods face challenges in accurately determining total audience ratings across multiple media platforms, particularly when duplication factors for media platform combinations are unknown, leading to inconsistencies and inefficiencies in data processing.
Innovation Solution
The implementation of a campaign mapping technique using a maximum entropy solver, which estimates duplication factors by mapping a query media campaign to a reference media campaign with known duplication factors, allowing for the calculation of unique audience metrics across different media platforms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional audience measurement methods are used to monitor media exposure of panelists, then audience size and demographic information can be obtained, but accurate determination of total audience ratings across multiple media platforms is difficult when duplication factors are unknown
Solution Approach 1:
The patent introduces maximum entropy solvers as an intermediary computational method to estimate duplication factors across media platforms. These solvers act as mediators that take known duplication factors from reference campaigns and interpolate to estimate unknown duplication factors for query campaigns, enabling accurate total audience measurement without direct observation of all platform combinations.
Solution Approach 2:
The patent creates a computational model that copies the structure and relationships from reference media campaigns (with known duplication factors) to query media campaigns (with unknown duplication factors). By mapping the duplication factor relationships from reference campaigns to query campaigns, the system transfers knowledge to estimate unknown values accurately.
2Measurement precision
If duplication factors for all media platform combinations are directly measured, then accurate total audience ratings can be determined, but the measurement process becomes inefficient and resource-intensive
Solution Approach 1:
The patent applies partial action by measuring and using only the duplication factors that are actually observed from panelist data, rather than attempting to directly measure all possible media platform combinations. The maximum entropy solver then completes the estimation for unobserved combinations based on the partial data available, achieving accurate results with reduced measurement effort.
Solution Approach 2:
The patent performs preliminary measurement of duplication factors from panelist exposure data before running the maximum entropy solver. This preliminary action collects all available observed duplication factors, which are then used as inputs to the solver to estimate the remaining unknown factors, streamlining the overall measurement process.
3Quantity of substance
If panelist data is collected across multiple media platforms, then audience exposure information can be gathered, but inconsistencies and errors arise when duplication factors are unknown
Solution Approach 1:
The patent transforms the problem from directly measuring unknown duplication factors to estimating them through parameter optimization. The maximum entropy solver changes the approach by optimizing the duplication factor parameters to satisfy constraints from observed panelist data, ensuring consistency across multiple media platforms while handling unknown factors.
Solution Approach 2:
The patent implements feedback by using observed panelist duplication factors as constraints that guide the maximum entropy solver's estimation process. The solver continuously adjusts its estimates against the observed data feedback, ensuring that the estimated duplication factors are consistent with actual measurements and reducing errors in the final audience metrics.
Data Source
AI summary
Example methods and apparatus disclosed herein include campaign mapping for total audience measurement. An example apparatus includes processor circuitry to train a machine learning model to determine first and second estimated duplication factors for respective first and second reference media campaigns; and determine, using the machine learning model, third estimated duplication factors for a query media campaign based on total exposure metrics associated with individual ones of media platforms for the query media campaign. The processor circuitry to select one of the first and second reference media campaigns based on a comparison of the third estimated duplication factors with each of the first and second estimated duplication factors; and determine fourth estimated duplication factors for the query media campaign based on (a) the respective first or second estimated duplication factors associated with the selected one of the first and second reference media campaigns and (b) the total exposure metrics.