Behavioral Targeting System Using Recency Intensity Frequency Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current online behavioral targeting systems lack the ability to effectively generate user profiles that accurately predict user interests and preferences for targeted advertising, leading to inefficient ad delivery and suboptimal user experiences.
Innovation Solution
A behavioral targeting system that utilizes a framework with multiple models and dimension parameters, including recency, intensity, and frequency, to generate user profile scores based on online activity data, allowing for personalized ad serving and improved user profiling across various marketing objectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional behavioral targeting systems are used to generate user profiles, then the system structure is simple, but the accuracy of predicting user interests and behaviors is insufficient
Solution Approach 1:
The system segments user profile generation into multiple independent models, each focusing on specific dimensions (recency, intensity, frequency). This allows complex prediction accuracy to be achieved through coordinated simple components, resolving the contradiction between accuracy and complexity.
Solution Approach 2:
The system introduces multiple dimension parameters (recency, intensity, frequency) to transform the user profile generation process. By changing from a single-parameter approach to multi-parameter modeling, the system achieves higher prediction accuracy while maintaining manageable complexity through structured parameter organization.
2Reliability
If multiple dimension parameters are introduced to improve user profile accuracy, then the prediction capability is enhanced, but the computational complexity increases
Solution Approach 1:
The computational workload is segmented across three distinct dimension models (recency, intensity, frequency), each handling specific calculations. This segmentation allows the system to achieve comprehensive prediction capability while distributing computational complexity across manageable, independent modules.
Solution Approach 2:
The multi-dimensional model framework serves multiple functions simultaneously: it improves prediction reliability, enables extensibility for different advertising scenarios, and provides a unified structure for processing various user behaviors. This multi-functionality justifies the computational complexity by delivering comprehensive system capabilities.
3Adaptability or versatility
If the system uses specific rules and weights for different advertising scenarios, then the adaptability to different marketing objectives is improved, but the system configuration complexity increases
Solution Approach 1:
The system employs a universal multi-dimensional model framework that can adapt to different advertising scenarios (brand advertising, direct response, etc.) through configuration rather than structural changes. This universality achieves high adaptability while avoiding the complexity of multiple specialized systems.
Solution Approach 2:
The system achieves adaptability to different marketing objectives by changing parameters (rules and weights) rather than changing the underlying system structure. This parameter-based adaptation allows flexible configuration for different scenarios while maintaining a simple, unified system architecture.
Data Source
AI summary
A behavioral targeting system determines user profiles from online activity. The system includes a plurality of models that define parameters for determining a user profile score. Event information, which comprises on-line activity of the user, is received at an entity. To generate a user profile score, a model is selected. The model comprises recency, intensity and frequency dimension parameters. The behavioral targeting system generates a user profile score for a target objective, such as brand advertising or direct response advertising. The parameters from the model are applied to generate the user profile score in a category. The behavioral targeting system has application for use in ad serving to on-line users.