Consumer Decision Tree Generation Using Retailer Transaction Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing consumer decision tree generation methods lack accuracy and authenticity due to reliance on biased data from brand manufacturers and require human intervention, making them inefficient and unscalable for retailers.
Innovation Solution
A computer system that automatically generates a consumer decision tree using retailer transaction data, calculating similarities between products and attributes to create an unbiased, customer-centric approach by identifying significant attributes and forming hierarchical structures that can be fully automated.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If consumer decision trees are generated using data from brand manufacturers, then the process can be simplified, but the accuracy and authenticity of the decision tree deteriorates due to biased data
Solution Approach 1:
The patent introduces retailer transaction data as an intermediary source instead of directly using brand manufacturer data. This intermediary data source provides unbiased, objective information about actual consumer purchasing behavior, resolving the contradiction by maintaining ease of generation while improving accuracy through neutral data collection.
Solution Approach 2:
The system enables retailers to self-generate their own consumer decision trees using their proprietary transaction data. This self-service approach eliminates dependency on biased external data sources while maintaining operational simplicity, allowing retailers to independently create accurate, authentic decision trees from their own business data.
2Reliability
If manual methods are used to generate consumer decision trees, then human insight can be incorporated, but the process becomes inefficient and unscalable
Solution Approach 1:
The patent replaces manual mechanical processes with automated computational algorithms. The system automatically processes transaction data, identifies products, determines attributes, and constructs decision trees through computer processing, eliminating manual intervention while maintaining reliability and scaling efficiently.
Solution Approach 2:
The system transforms the generation process from manual to automated by changing the fundamental parameter of data processing methodology. By using computational algorithms to analyze transaction data and automatically construct decision trees, the system achieves both high productivity and maintained authenticity without human intervention.
3Ease of manufacture
If existing CDT generation methods are used, then the process can be completed, but the scalability to large datasets deteriorates
Solution Approach 1:
The patent segments the consumer decision tree generation process into distinct automated steps: data reception, product identification, attribute determination, and tree construction. This segmentation allows each component to be optimized independently and scaled efficiently, enabling the system to handle large datasets while maintaining feasibility through modular processing.
Data Source
AI summary
A system generates a consumer decision tree (“CDT”). The system receives customer purchasing data that includes transactions of a plurality of products each having at least one product attribute. For a product category, the system identifies a plurality of similar products from the purchasing data and one or more attributes corresponding to each similar product. The system assigns the product category as a current level of the CDT, and determines a most significant attribute of the plurality of attributes for the current level. The system forms a next level of the CDT by dividing the most significant attribute into a plurality of sub-sections, where each sub-section corresponds to an attribute value of the most significant attribute. The system then forms a next level of the CDT for each sub-section until a terminal node is identified.