Targeted Content Transmission Using Machine Learning Affinity Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional targeted advertising approaches are often too broad, leading to increased costs due to inefficiencies in identifying and reaching consumers most likely to engage with digital content, as current systems struggle to effectively process and utilize the large volumes of consumer data available.
Innovation Solution
A method and system utilizing machine learning models, specifically field-aware factorization machines, to analyze user metadata including browsing history, purchase history, social media posts, and location information to identify users with an affinity for purchasing digital home-entertainment content, allowing for targeted content transmission to those with a demonstrated interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If broad targeted advertising campaigns are used to reach potential consumers, then the coverage and reach of the campaign is improved, but the cost and inefficiency increase due to targeting users unlikely to engage
Solution Approach 1:
The patent segments the broad consumer base into specific groups based on device usage patterns, content consumption behavior, and engagement metrics. By dividing the target audience into segments with demonstrated affinity for digital content, the system maintains broad coverage while focusing advertising resources on high-probability users, thereby reducing waste and cost.
Solution Approach 2:
The patent changes the parameters used for targeting from demographic generalizations to behavioral metrics such as device usage frequency, content consumption patterns, and engagement history. This parameter transformation enables more precise identification of users likely to engage with digital content, improving cost-efficiency while maintaining adequate coverage.
2Measurement precision
If traditional advertising systems process consumer data to identify target audiences, then the targeting capability is improved, but the system becomes overwhelmed by the large volume of data produced by consumers
Solution Approach 1:
The patent extracts and focuses on specific, high-value data elements from the overwhelming consumer data stream, such as device usage patterns, content consumption behavior, and engagement metrics. By selecting only the most relevant data points rather than processing all available consumer data, the system achieves high targeting accuracy while managing data processing complexity.
Solution Approach 2:
The patent introduces an intermediary processing layer that filters, aggregates, and pre-processes consumer data before it reaches the targeting algorithm. This intermediary system reduces the raw data volume and presents processed, actionable insights to the targeting engine, thereby maintaining precision while reducing overall system complexity.
3Measurement precision
If machine learning models analyze user metadata to identify users with affinity for purchasing digital content, then the targeting precision is improved, but the computational resources and processing time increase
Solution Approach 1:
The patent applies machine learning models selectively to subsets of users identified through initial filtering based on device usage patterns and content consumption behavior. Rather than applying complex ML analysis to all users, the system performs partial analysis on high-probability candidates, achieving high accuracy while reducing computational energy consumption.
Solution Approach 2:
The patent performs preliminary filtering and preprocessing of user data using simpler, computationally efficient methods before applying machine learning models. By pre-identifying users with demonstrated affinity for digital content through behavioral metrics, the system reduces the dataset requiring intensive ML processing, thereby lowering energy consumption while maintaining identification accuracy.
Data Source
AI summary
According to at least one embodiment, a method for providing secondary content, related to primary content, for targeted transmission, includes: receiving a set of user metadata for a plurality of users, the user metadata comprising one or more of user browsing history, purchase history, term usage history, social media posts and actions, or location information; based on the set of user metadata, identifying, via a machine learning model, a subset of the users having an affinity for purchasing digital home-entertainment content, wherein the affinity is above a threshold level; and providing an indication of the subset of users having the affinity above the threshold level.