Incrementality Attribution Models for Multi-Exposure Content Contribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
It is difficult to determine the relative contributions of various online content exposures to a user's subsequent performance of a specified target action, particularly when these exposures occur at different times and involve both organic and digital components.
Innovation Solution
A model is created to represent relationships between user attributes, content exposures, and performance levels, using organic and third-party exposure data to attribute incremental performance levels to digital components, and adjust transmission criteria based on these attributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple content exposures are tracked to improve attribution accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent segments the attribution problem into distinct components: organic exposures, paid exposures, and target actions. Each type of exposure is tracked separately with unique identifiers, allowing the system to calculate incremental attribution for each segment without requiring a monolithic tracking approach that would increase complexity.
Solution Approach 2:
The patent introduces an intermediary attribution model that processes exposure data and calculates incremental performance levels. This intermediary layer sits between raw exposure tracking and final attribution results, simplifying the overall system architecture by centralizing the complex calculation logic in a dedicated component rather than distributing it throughout the entire system.
2Measurement precision
If incremental performance levels are calculated for each exposure, then measurement precision improves, but loss of time increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing exposure data and organizing it into structured formats before attribution calculations are needed. Exposure data is collected and validated in advance, with identifiers and timestamps prepared for rapid processing during attribution calculations, reducing the time required for actual incremental performance level computation.
Solution Approach 2:
The patent changes parameters by focusing calculations on incremental performance levels rather than total performance. By calculating only the marginal contribution of each exposure (the incremental effect) rather than recalculating entire attribution chains, the system achieves precise measurement with reduced computational time and resource requirements.
Data Source
AI summary
Methods, systems, and computer programs encoded on a computer storage medium, for training and using machine learning models are disclosed. Methods include creating a model that represents relationships between user attributes, content exposures, and performance levels for a target action using organic exposure data specifying one or more organic exposures experienced by a particular user over a specified time prior to performance of a target action by the particular user and third party exposure data specifying third party exposures of a specified type of digital component to the particular user over the specified time period. Using the model, an incremental performance level attributable to each of the third party exposures at an action time when the target action was performed by the particular user is determined. Transmission criteria for at least some digital components to which the particular user was exposed are modified based on the incremental performance.