Optimizing Content Delivery for Non-Measurable Users
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online content providers face challenges in measuring and optimizing electronic content delivery efficiency due to increased user opt-out options and reduced availability of tracking mechanisms, making it difficult to maximize in-target impressions for non-measurable users.
Innovation Solution
A computer-implemented method and system that estimate the probability of electronic content meeting targeting requirements by using feature vectors and in-target indications for measurable users, generating an in-target rate control signal, and adjusting delivery conditions for non-measurable users based on this analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If tracking mechanisms such as cookies and tracking pixels are used to measure user behavior, then the in-target rate of delivered impressions is improved, but the availability and effectiveness of these mechanisms deteriorates due to user opt-out options and reduced user consent
Solution Approach 1:
The patent introduces an intermediary approach by using measurable users as a proxy group to infer characteristics of non-measurable users. Instead of directly tracking non-measurable users, the system measures a subset of users and uses their behavior patterns to estimate delivery optimization parameters for the broader user population, thereby circumventing the limitation of reduced tracking availability.
Solution Approach 2:
The system creates a representative copy or model of the non-measurable user population by analyzing measurable users. It generates synthetic delivery optimization strategies based on patterns observed in measurable users, effectively copying the behavior and response patterns to apply to users who cannot be directly tracked, thus maintaining measurement precision without relying on direct tracking of all users.
2Productivity
If user tracking and measurement mechanisms are expanded to capture more user behavior data, then the ability to optimize content delivery is improved, but the complexity of the system increases due to handling opt-out options and consent management
Solution Approach 1:
The patent extracts the optimization problem from the complex tracking infrastructure by separating measurable users from non-measurable users. It removes the need to directly track and measure non-measurable users by focusing computational resources only on the measurable subset, thereby simplifying the system while maintaining optimization capability for the entire user population.
Solution Approach 2:
The system segments the user population into measurable and non-measurable groups, applying different measurement and optimization strategies to each segment. This segmentation allows the system to maintain high productivity for measurable users while avoiding the complexity of directly tracking non-measurable users, as optimization for the latter is derived indirectly from the former.
3Productivity
If content delivery is targeted to meet specific user criteria, then the efficiency and desired outcomes are improved, but the difficulty of identifying and measuring users meeting these criteria increases due to reduced tracking availability
Solution Approach 1:
The patent uses measurable users as an intermediary group to detect and measure user criteria for non-measurable users. By analyzing the behavior and characteristics of measurable users who meet specific criteria, the system infers which non-measurable users are likely to meet the same criteria, thereby maintaining content delivery efficiency without direct measurement of all users.
Solution Approach 2:
The system performs preliminary measurement and analysis on measurable users before applying the findings to non-measurable users. It pre-establishes delivery optimization parameters based on measurable user data, which are then applied to non-measurable users in advance, reducing the need for real-time detection and measurement during actual content delivery.
Data Source
AI summary
A computer-implemented method for optimizing electronic content delivery for non-measurable users includes receiving a feature vector for each electronic content impression opportunity, receiving a feature vector for each delivered item of electronic content for measurable users, receiving an in-target indication for each delivered item of electronic content for measurable users, estimating a probability that an electronic content impression opportunity with a specified feature vector will meet targeting requirements based on the received feature vectors and the received in-target indications, receiving an in-target threshold value, generating an in-target rate control signal based on a number of total delivered items of electronic content for measurable users and a number of in-target delivered items of electronic content for measurable users, determining whether the estimated probability is greater than the in-target rate control signal, and generating conditions for delivering a new item of electronic content for an electronic content impression opportunity.