Cognitive Analysis System for Unexpressed User Preferences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Retailers face challenges in determining users' unexpressed likes and dislikes, leading to missed sales opportunities due to the difficulty in quantifying lost sales and tracking user preferences, especially when users do not communicate reasons for not purchasing certain items.
Innovation Solution
A cognitive analysis system that processes user preferences, purchase history, and behavioral patterns to identify both overt and covert likes and dislikes, and recommends a prioritized list of items from a retailer's inventory, including substitutes for unavailable liked items, while providing feedback on lost opportunities to retailers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If retailers collect and analyze user preference data to identify unexpressed likes and dislikes, then user satisfaction and sales improvement are enhanced, but system complexity and data processing requirements increase
Solution Approach 1:
The cognitive analysis system segments user preferences into distinct categories (overt likes, covert likes, overt dislikes, covert dislikes) and processes each segment separately. This segmentation allows the system to handle complex preference data in manageable units, reducing overall system complexity while maintaining comprehensive analysis capabilities for identifying unexpressed likes and dislikes.
Solution Approach 2:
The patent introduces a cognitive analysis system as an intermediary layer between raw user preference data and retail decision-making. This intermediary processes and interprets unexpressed preferences, transforming complex behavioral data into actionable insights about user likes and dislikes, thereby enabling sales improvement without requiring retailers to directly manage the complexity of raw preference data.
2Measurement precision
If the system analyzes unexpressed preferences using cognitive analysis, then accuracy in item recommendation improves, but computational resources and analysis time increase
Solution Approach 1:
The system performs preliminary analysis by collecting and organizing user preference data into structured categories (overt/covert likes and dislikes) before conducting the actual cognitive analysis to identify unexpressed preferences. This preliminary structuring of data accelerates the subsequent analysis process while maintaining high accuracy in detecting unexpressed likes and dislikes, reducing the overall computational time required.
3Ease of operation
If retailers exclude items with disliked characteristics from recommendations, then user satisfaction improves, but potential sales opportunities may be lost
Solution Approach 1:
The patent applies local quality by differentiating between various types of dislikes (overt vs. covert) and applying different recommendation strategies for each. Instead of uniformly excluding all items with disliked characteristics, the system selectively filters items based on the specific type and strength of user dislike, thereby maintaining user satisfaction while preserving sales opportunities for items that may be acceptable substitutes or that the user might reconsider.
Data Source
AI summary
An unexpressed liking and an unexpressed dislike of a user, which are not specified in the user's preference are determined by cognitive analytics. The unexpressed liking and dislike correspond to a first and second characteristic of items, respectively. In a list, a first item having the first characteristic and available in an inventory is included, which is, and a second item having the second characteristic and also available in the inventory is excluded. Items included in the list are arranged according to the user's degrees of liking or the items. An item having the first characteristic is determined to be absent from the inventory. Using completed sales information received from a set of retailer systems, an estimated value of a lost sales opportunity produced when the absent item is purchased is computed. The prioritized list and an accommodation offer responsive to the cost of the lost opportunity are presented.