Affinity Attribute Model for Campaign Target Group Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current campaign management applications lack an effective method to determine a target group of users based on product-specific affinity attributes, leading to inefficient campaign content dissemination and reduced engagement.
Innovation Solution
A system that utilizes machine learning to generate affinity attribute models and inclusion/exclusion score functions, considering product-specific, confirmable, and inferred user attributes with adjustable weights, to precisely select a target group of users for campaign content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional segmentation approach is used to select target audience, then campaign content can be disseminated to users, but the campaign content effectiveness and engagement are reduced due to lack of product-specific affinity consideration
Solution Approach 1:
The patent segments users based on multiple dimensions including product-specific affinity attributes, confirmable attributes, and inferred attributes. This multi-dimensional segmentation enables precise identification of target users who have high affinity towards specific product attributes, thereby improving campaign effectiveness while maintaining manageable complexity through structured attribute categories
Solution Approach 2:
The patent introduces adjustable weights for different attribute types (product-specific affinity, confirmable, inferred) that can be modified to optimize target group selection. By changing these parameter weights, the system can adapt to different campaign requirements and balance between precision and computational complexity
2Productivity
If product-specific affinity attributes with adjustable weights are used to determine target group, then campaign content effectiveness is enhanced, but the system complexity increases due to machine learning models and multiple attribute types
Solution Approach 1:
The patent pre-generates affinity attribute models using machine learning before campaign execution. These models are trained on historical data to predict user affinity towards product attributes, allowing the system to leverage pre-computed insights during actual campaigns and reducing real-time computational complexity while maintaining high productivity
Solution Approach 2:
The patent introduces an intermediary layer of affinity attribute models that bridge raw user data and campaign target selection. These models act as mediators that translate complex user behavior patterns into actionable affinity scores, simplifying the overall system architecture while enabling sophisticated target group determination
3Measurement precision
If traditional user segmentation is used, then campaign content can be disseminated to broad user groups, but interaction and purchase likelihood are reduced
Solution Approach 1:
The system performs preliminary machine learning model generation to create affinity attribute models before campaign execution. This advance preparation enables rapid, precise user affinity assessment during actual campaigns, achieving high measurement precision without excessive time loss during campaign deployment
Solution Approach 2:
The patent uses inferred user attributes that replicate or copy actual user preferences and behaviors based on historical data patterns. By creating these attribute copies, the system can quickly assess user affinity without extensive real-time analysis, balancing precision with time efficiency
Data Source
AI summary
A campaign profile specifies products and/or content items associated with a campaign. A target group selection engine applies an affinity attribute model to user information of a user. The affinity attribute model is used to determine the user's affinity towards (a) product attributes of the products associated with the campaign and/or (b) content attributes of the content items associated with the campaign. The affinity attribute model may be generated using machine learning. A user interface accepts target user tuning parameters that specify weights to be applied to the affinity attributes determined by the affinity attribute model. Based at least on applying the weights to the affinity attributes, an inclusion score and/or exclusion score for the user is determined. The user is included in a target group, for engaging with the campaign, based on the inclusion score and/or exclusion score.