Attribution Adjusting for External Viewing Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing attribution techniques for online consumer touchpoints fail to accurately account for external viewing conditions, leading to insufficiently targeted and effective ad placements.
Innovation Solution
Systems and methods that determine external viewing conditions, such as ambient noise and device movement, to adjust attribution credits for online consumer touchpoints, ensuring more accurate credit assignment based on the effectiveness of ads in various environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing attribution techniques are used without considering external viewing conditions, then the attribution process is simple and fast, but the accuracy and effectiveness of ad placements are insufficient
Solution Approach 1:
The patent segments the attribution process by introducing environment-specific effectiveness metrics. Instead of treating all consumer interactions uniformly, the system divides attribution into multiple segments based on external viewing conditions (e.g., mobile environment, desktop environment, distracting environment, focused environment). Each segment has its own effectiveness weight, allowing for more precise measurement of attribution accuracy without requiring complete system redesign.
Solution Approach 2:
The patent changes the parameter of ad effectiveness by introducing environment-dependent weightings. The effectiveness of a consumer interaction is no longer a fixed value but varies based on external conditions detected during the interaction. For example, the same ad interaction may have different effectiveness weights depending on whether it occurred in a distracting environment or a focused environment, thereby improving attribution accuracy through parameter adaptation.
2Productivity
If attribution does not account for external viewing conditions, then computing resources are conserved, but ad placements are not sufficiently targeted or effective
Solution Approach 1:
The patent applies preliminary action by detecting and recording external viewing conditions at the time of each consumer interaction. The system proactively captures environment data (such as device type, location, time of day, and distraction indicators) before the attribution calculation is performed. This preliminary collection of environmental context enables more effective ad placement decisions without requiring intensive real-time computing resources during the attribution phase.
Solution Approach 2:
The patent uses lightweight, easily obtainable data proxies to represent external viewing conditions rather than requiring complex, resource-intensive measurements. For example, the system uses simple device metadata, timestamp-based time-of-day analysis, and basic location data as inexpensive proxies for determining environment type. These low-cost data points provide sufficient information to adjust attribution effectiveness without consuming excessive computing resources.
3Measurement precision
If external viewing conditions are detected and used to adjust attribution, then credit allocation becomes more accurate, but the attribution process becomes more complex
Solution Approach 1:
The patent applies local quality by assigning different effectiveness weights to consumer interactions based on their specific environmental context. Rather than applying a uniform complexity-adjusted model to all interactions, the system tailors the attribution calculation to each individual interaction's local conditions. For example, interactions occurring in mobile environments with high distraction indicators receive different weighting than desktop interactions in focused environments, achieving high credit allocation accuracy through localized adjustment.
Solution Approach 2:
The patent introduces dynamics into the attribution process by making effectiveness weights adaptive rather than static. The system dynamically adjusts the weight of each consumer interaction based on real-time or near-real-time detection of external viewing conditions. This dynamic approach allows the attribution process to automatically adapt to varying environmental contexts without requiring manual reconfiguration or complex rule-based systems, balancing accuracy with process simplicity.
Data Source
AI summary
Systems and methods are disclosed herein for attributing credit to online consumer touchpoints for a consumer performing an action. The systems and methods involve determining whether a consumer is in a particular environment for an online consumer touchpoint by detecting an external viewing condition for the consumer for the online consumer touchpoint. The systems and methods determine that the consumer performed an action, such as a conversion, following the online consumer touchpoint and additional online consumer touchpoints. An effectiveness of the online consumer touchpoint in the particular environment is determined and used to attribute relative credit to the online consumer touchpoint and the additional online consumer touchpoints for the consumer performing the action.