ML Segment Targeting for Digital Content Delivery Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional digital content delivery systems face inefficiencies due to inaccurate predictions of user attributes, leading to off-target digital content deliveries, wastage of computational resources, and inability to predict user visitation likelihood, resulting in inefficient targeted content delivery.
Innovation Solution
A machine learning-based segment targeting system generates training data by segmenting users based on content viewing patterns, inferring user-demographic correlations, and predicting revisit probabilities to identify users most likely to match a target demographic, thereby optimizing targeted content delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional predictive models are used to categorize consumers into demographics, then digital content can be delivered to targeted audiences, but off-target deliveries increase and computational resources are wasted
Solution Approach 1:
The patent segments users into distinct groups based on content consumption patterns rather than using traditional demographic categories. By dividing the user base into behavior-based segments, the system achieves more accurate targeting without wasting resources on off-target deliveries to users who don't match the intended audience.
Solution Approach 2:
The patent replaces conventional demographic-based predictive models with a machine learning model that analyzes content consumption patterns. This substitution eliminates reliance on inaccurate demographic assumptions and human-involvement errors, providing more accurate predictions of user attributes and reducing off-target content deliveries.
2Ease of manufacture
If third party data is used to generate predictive models, then model generation is enabled, but data accuracy decreases and consumer attribute specificity is lost
Solution Approach 1:
The system generates its own training data by analyzing content consumption patterns from its own platform, eliminating dependence on third-party data sources. This self-service approach ensures the data maintains high consumer attribute specificity and accuracy while still enabling effective model generation through automated machine learning processes.
3Adaptability or versatility
If supplemental digital content is delivered with primary digital content, then targeted content delivery is enabled, but resource wastage increases due to off-target deliveries
Solution Approach 1:
The system uses machine learning models to continuously analyze content consumption patterns and refine user segmentation based on actual behavior feedback. This feedback mechanism enables more accurate prediction of which users will engage with supplemental content, reducing resource wastage by avoiding delivery to users unlikely to consume the content.
Solution Approach 2:
The system performs preliminary analysis of user content consumption patterns before delivering supplemental digital content. By pre-segmenting users based on their demonstrated interests and consumption behaviors, the system can proactively identify target audiences and deliver supplemental content only to relevant users, preventing resource wastage beforehand rather than correcting it after delivery.
Data Source
AI summary
Techniques are described for machine learning-based generation of target segments is leveraged in a digital medium environment. A segment targeting system generates training data to train a machine learning model to predict strength of correlation between a set of users and a defined demographic. Further, a machine learning model is trained with visit statistics for the users to predict the likelihood that the users will visit a particular digital content platform. Those users with the highest predicted correlation with the defined demographic and the highest likelihood to visit the digital content platform can be selected and placed within a target segment, and digital content targeted to the defined demographic can be delivered to users in the target segment.