Dynamic Product Module Ranking for Ecommerce Upsell
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information handling systems face challenges in determining which product options to display and their optimal order, particularly in ecommerce, as existing approaches rely on intuition and sales data rather than behavioral data of online visitors.
Innovation Solution
A system and method that generate a numeric ranking value, ConfigRank, for product modules based on upsell propensity, revenue, and user interaction data to determine their placement within a user interface, using metrics like Hit Num Rank, Upsell Hit Num Rank, and Upsell Revenue per Upsell Hit Num Rank, to prioritize product module descriptors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If product modules are displayed in traditional order (e.g., processor followed by memory), then the user interface maintains simplicity and ease of operation, but user interactions and revenue are suboptimal because the order is based on intuition rather than behavioral data
Solution Approach 1:
The patent implements dynamic ordering of product module descriptors based on calculated ConfigRank values. The system automatically adjusts the display order of modules (such as processor, memory, storage) according to their calculated rankings, transforming the static, intuition-based ordering into a dynamic, data-driven ordering that adapts to user behavior patterns and revenue optimization goals
Solution Approach 2:
The system changes the ordering parameter from traditional categorical sequencing to a numerically calculated ConfigRank parameter. This parameter is derived from multiple factors including Hit Num Rank, Upsell Hit Num Rank, upsell Hit Pct Rank, and Upsell Revenue per Upsell Hit Num Rank, transforming the display order based on quantifiable performance metrics rather than fixed conventions
2Adaptability or versatility
If vendors display all 50 or more available modules to customers, then complete product options are available, but the user interface becomes complex and overwhelming, reducing ease of operation
Solution Approach 1:
The system extracts and prioritizes the most relevant product modules for display based on ConfigRank calculations. Instead of presenting all 50+ available modules, the system selects and displays only the top-ranked modules that are most relevant to user needs and revenue generation, effectively filtering out less important options while maintaining access to the complete product catalog
Solution Approach 2:
The patent applies different display priorities to different product modules based on their individual ConfigRank values. High-ranking modules receive prominent display positions with greater visibility, while lower-ranking modules are either displayed in less prominent positions or made available on demand, creating a differentiated display strategy that optimizes both completeness and usability
3Productivity
If product modules are ordered to maximize user interactions, then revenue potential increases, but the ordering becomes complex requiring analysis of multiple behavioral metrics
Solution Approach 1:
The patent segments the complex ordering problem into four distinct ranking components: Hit Num Rank (user interaction frequency), Upsell Hit Num Rank (upsell conversion count), upsell Hit Pct Rank (upsell conversion rate), and Upsell Revenue per Upsell Hit Num Rank (revenue efficiency). Each component is calculated separately using specific behavioral metrics, and then combined through weighted summation to produce the final ConfigRank, breaking down the complex optimization problem into manageable segments
Solution Approach 2:
The system implements feedback loops by continuously analyzing user behavioral data (clicks, views, conversions, revenue) and using this information to calculate and update ConfigRank values. This feedback mechanism allows the ordering system to learn from user interactions and automatically adjust module priorities to maximize revenue while adapting to changing user preferences and behaviors
Data Source
AI summary
A system, method, and computer-readable medium are disclosed for managing the display of product module descriptors within a user interface. Product module data, along with historical visit and product module purchase data, is processed to generate a Config Score numeric value, which in turn is processed to generate a ConfigRank numeric value for each of a plurality of product modules. In turn, the ConfigRank numeric values are then used to determine the placement of each product module's associated product module descriptor within a user interface window.