Behavioral Targeting System Using Recency Intensity Frequency Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current behavioral targeting systems lack the ability to effectively predict user propensity for success in achieving marketing objectives, such as brand awareness and direct response advertising, by not adequately analyzing and utilizing online user behavior data to personalize content and advertisements.
Innovation Solution
A behavioral targeting system that generates user profiles based on online activity data, using models and rules to determine user scores for various marketing objectives, including direct response advertising, brand awareness, and purchase intention, by categorizing events and applying dimensions like recency, intensity, and frequency to predict user interest and serve relevant content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If behavioral targeting systems use online activity data to predict user propensity for marketing objectives, then user profile accuracy and personalization effectiveness improve, but system complexity and data processing requirements increase
Solution Approach 1:
The system segments user behavior analysis into distinct event types (clicks, views, conversions) and categorizes them into specific interest areas. Each event type is processed through separate scoring mechanisms that evaluate different aspects of user engagement, allowing the system to maintain high prediction accuracy while managing complexity through modular processing of different behavior dimensions independently.
Solution Approach 2:
The system introduces multiple scoring dimensions beyond simple interest categorization, including recency weighting, frequency analysis, and conversion probability scoring. These additional dimensions allow the system to predict user propensity for specific marketing objectives by evaluating behavior from multiple angles simultaneously, improving accuracy while distributing computational complexity across different analytical layers.
2Productivity
If the system analyzes detailed online behavior data to generate personalized user profiles, then user engagement and conversion rates improve, but data processing time and computational resources increase
Solution Approach 1:
The system pre-processes and categorizes user behavior events as they occur, assigning preliminary scores and interest area classifications in real-time. Event data is structured and stored in categorized formats before needed for profile generation, allowing rapid retrieval and analysis when creating or updating user profiles, thus reducing processing time while maintaining detailed analysis capabilities.
Solution Approach 2:
The system dynamically adjusts analysis parameters based on user behavior patterns and marketing objective types. For example, recency weights are modified based on event type, and scoring thresholds are adjusted according to the specific marketing campaign goals. This flexibility allows the system to optimize processing efficiency for different scenarios while maintaining high conversion rate prediction accuracy.
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, is 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.