Alternative Item Booster Service Using Word2Vec for Private-Label Substitution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Retailers lack automated tools to efficiently promote and suggest private label items as alternatives to branded items, leading to suboptimal sales and reduced profitability.

Innovation Solution

A system utilizing a Word2Vec algorithm to generate item vectors in a multidimensional space, determining similarities between branded and private label items based on transaction histories, and integrating machine learning to provide real-time recommendations for private label item substitutions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual efforts are used to promote private label items, then retailers can maintain some level of private label sales, but the effort and time required from multiple departments increases significantly

Engineering Contradiction:

Improveprivate label sales efficiencyVSAvoidtime spent by departments

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system enables private label promotion to serve itself by automatically analyzing transaction data, identifying substitution opportunities, and generating recommendations without requiring manual intervention from marketing, merchandising, or finance departments

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical process of departmental coordination with an automated computational system that uses machine learning algorithms to analyze data and generate promotion strategies

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated tools are implemented to promote private label items, then sales efficiency and profitability improve, but system complexity and implementation difficulty increase

Engineering Contradiction:

Improveprivate label sales efficiencyVSAvoidautomation system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system performs multiple functions including data analysis, recommendation generation, and performance tracking within a single integrated platform, reducing the need for separate complex systems for each function

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary layer that translates complex data analysis into simple, actionable recommendations that can be easily implemented by retail staff without requiring them to understand the underlying system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If data-driven recommendations are provided to customers, then private label item visibility and sales increase, but the need for advanced analytics infrastructure and processing power increases

Engineering Contradiction:

Improvecustomer guidance accuracyVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of informationVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary analysis of transaction data to pre-compute item relationships and substitution patterns, so that when a customer makes a selection, the recommendation can be generated quickly without requiring intensive real-time computation

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12373877B2Alternative item booster service

Publication Date: 2025.07.29 NCR VOYIX CORP

AI summary

Item vectors representing transaction contexts for items are mapped to multidimensional space. A request is received for an alternative to a given item from a resource. The multidimensional space is evaluated to identify closest candidate items to the given item based on the corresponding item vectors. An optimal candidate item is selected from the candidate items based on the request. The association between the given item and the optimal candidate item is injected within a process workflow associated with the resource.