Line Recommendation Engine for Item Pricing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual item linkage processes in pricing systems are time-consuming and lack rigor, especially in complex categories with numerous attribute combinations, limiting the ability to create consistent line groups and maintain pricing consistency.
Innovation Solution
An automated system utilizing a line recommendation engine with a single-class support vector model for new line detection and a nearest neighbor evaluator for existing line matching, which recommends line assignments based on item attributes and adjusts parameters for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual item linkage processes are used, then pricing managers can perform item linkage checks, but the process is time-consuming and lacks rigor
Solution Approach 1:
The system enables automated self-service item linkage by training a machine learning model on historical item data and attributes. The model automatically assigns items to lines based on learned patterns from training data, eliminating the need for manual item linkage checks while maintaining or improving rigor through consistent application of learned rules.
Solution Approach 2:
The patent replaces the mechanical manual process of item linkage with an automated machine learning system. The system uses algorithms to process item attributes and determine line assignments, substituting human manual checks with computational automation that operates faster and more consistently.
2Extent of automation
If rules-based approaches are used for item linking, then some automation is achieved, but users must be aware of attributes defining each line which becomes untenable in complex categories
Solution Approach 1:
The machine learning model performs self-service by automatically learning which attributes are important for line assignment from training data. Instead of requiring users to pre-define all relevant attributes and rules, the system independently identifies and weights attributes based on historical patterns, handling complex attribute combinations without user intervention.
Solution Approach 2:
The system dynamically adjusts parameter weights and thresholds based on learned patterns from training data. Rather than using fixed rules defined by users, the model learns optimal parameter configurations for different item categories, adapting to complex scenarios by changing parameters based on empirical evidence from historical data.
3Ease of operation
If manual replenishment groups are used, then item linkage can be assisted, but the process is very time-consuming
Solution Approach 1:
The patent replaces manual replenishment group processes with automated machine learning-based line assignment. The system automatically processes items through the trained model, which rapidly determines appropriate line assignments based on item attributes, eliminating the time-consuming manual operations while maintaining ease of use through automated decision-making.
Data Source
AI summary
Systems and methods for item price assignment. A line recommendation engine receives unassigned records from a queue and stores one or more line recommendations for the unassigned item record in a recommendation database. The line recommendation engine can determine a new line should be recommended, and/or which existing lines the unassigned item record could be assigned to. A user interface can display the one or more line recommendations for the unassigned item record to a user and receive an input indicating a selected line identifier for the unassigned item record. A machine learning engine can modify a parameter of the line recommendation engine based on the selected line identifier.