Dynamic Audience Identification via Machine Learning Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers face challenges in efficiently identifying and grouping target audiences based on user interests due to the need for large amounts of data and manual setup of parameters, leading to incorrect user classification and a negative user experience.
Innovation Solution
An experiment system employing a machine learning algorithm that automatically identifies target audiences by analyzing user browsing histories, using keywords provided by content providers to determine interest scores and dynamically adjust audience classifications without requiring manual rule setup.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual setup of parameters and rules is used for audience identification, then content providers can control audience grouping, but the process requires large amounts of data, significant time investment, and results in incorrect user classification
Solution Approach 1:
The system enables automatic audience identification where the machine learning algorithm autonomously analyzes user browsing histories and segments audiences without requiring manual parameter setup or rule configuration by content providers, eliminating time-consuming manual processes while maintaining classification accuracy
Solution Approach 2:
Manual mechanical processes of parameter setting and rule-based audience segmentation are replaced with an automated machine learning system that processes user data and performs audience identification algorithmically, significantly reducing the time required while improving classification precision
2Adaptability or versatility
If manual rule setup is used for audience grouping, then content providers can define target audiences, but the complexity of setting up parameters and rules increases
Solution Approach 1:
The machine learning system automatically performs audience segmentation and adapts to different content provider needs without requiring manual configuration of complex parameters or rules, maintaining versatility while eliminating setup complexity
Solution Approach 2:
The machine learning algorithm provides a universal audience identification system that can adapt to various content provider requirements and audience types without requiring separate parameter setups or rule configurations for each case
3Productivity
If traditional audience identification methods are used, then audiences can be identified, but large amounts of data are required and manual processing is needed
Solution Approach 1:
Manual data processing and audience identification operations are replaced with automated machine learning algorithms that efficiently process user browsing history data, significantly improving productivity while maintaining effective use of data resources
Data Source
AI summary
A browsing history associated with a user of a client device is received from the client device. One or more keywords associated with a target audience for a variant of a web page are received from a content provider system. A score is determined for the user based on the browsing history for the user and the one or more keywords associated with the target audience. The user is identified as part of the target audience based on the score for the user satisfying a score threshold. The variant of the web page is caused to be presented at the client device associated with the user.