Conversion Crediting via Time-Window Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advertisers face challenges in determining the contribution of online advertisements to conversion events, as existing methods lack precision in attributing the influence of multiple advertisements on consumer decisions, leading to unclear return on investment.
Innovation Solution
The system determines the contribution of advertisements to conversion events by selecting time windows, counting advertising events within these windows, applying a weighting model that exponentially decreases with time, and normalizing the results to provide a credit representing the advertisement's association strength with the conversion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional advertising attribution methods are used, then the process is simple to implement, but the measurement precision of advertisement contribution is insufficient
Solution Approach 1:
The patent segments the advertisement-to-conversion process into discrete time windows, counting advertising events in each window and applying separate weighting factors. This segmentation allows precise measurement of advertisement contribution at different time points while maintaining manageable computational complexity through structured breakdown of the attribution problem.
Solution Approach 2:
The patent introduces adjustable parameters including time window sizes, weighting factor functions, and normalization constants. These parameters can be modified to optimize measurement precision for different advertising scenarios without fundamentally changing the system architecture, allowing flexible adaptation while preserving computational efficiency.
2Measurement precision
If multiple time windows and weighting models are used to improve attribution accuracy, then the measurement precision increases, but the computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-defining time windows, weighting factor functions, and normalization constants before processing advertising events. This preliminary setup reduces computational complexity during actual attribution calculations, as the system only needs to count events and apply pre-computed weights rather than performing complex optimization in real-time.
Solution Approach 2:
The system uses self-service mechanisms where the weighting model automatically adjusts its parameters based on observed conversion patterns and time decay. The normalization process automatically scales credits without manual intervention, reducing computational overhead while maintaining high measurement precision through adaptive parameter tuning.
3Measurement precision
If weighting factors that exponentially decrease with time are applied, then the association strength measurement becomes more accurate, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent introduces time window counts as an intermediary metric between raw advertising events and final credit attribution. This intermediary layer simplifies measurement by aggregating events into discrete time buckets before applying exponential weighting, making the complex time-decay measurement more manageable while preserving accuracy through structured intermediate representation.
Data Source
AI summary
Methods, systems, and apparatus, including computer program products, for processing events related to presented content. In one aspect, a method includes determining a time window count of a number of advertising events associated with an advertisement during at least one time window before a conversion event; and determining a credit that represents a strength of an association between the advertisement and the conversion event, wherein determining a credit includes selecting a weighting model for the at least one time window count.