Retailer-Competitor Metadata Filtering for Alternative Product Ranking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems face challenges in efficiently identifying and recommending alternative products due to the complexity of natural language processing, reliance on inaccurate human-generated metadata, and the inefficiency of computational methods, leading to confusion and time-consuming processes in both brick and mortar retail and e-commerce environments.

Innovation Solution

A method and system utilizing machine learning algorithms, including lexical and semantic similarity analysis, to standardize and filter metadata from retailer and competitor products, calculate similarity scores, and rank alternatives based on feature importance, optimizing computational efficiency and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning algorithms with lexical and semantic similarity analysis are used to identify alternative products, then recommendation accuracy is improved, but computational time and complexity increase

Engineering Contradiction:
Improverecommendation accuracyVSAvoidcomputational time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by collecting and standardizing metadata from multiple sources before the actual product recommendation process. Metadata is gathered from product labels, descriptions, and other sources, then standardized into a common format with consistent data types and structures. This pre-processing creates a ready-to-use standardized metadata repository that can be quickly queried during recommendation generation, reducing computational time while maintaining high accuracy through the use of pre-processed lexical and semantic similarity features.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If extensive metadata from multiple sources is collected and analyzed, then product comparison comprehensiveness is improved, but data processing complexity increases

Engineering Contradiction:
Improveproduct comparison comprehensivenessVSAvoiddata processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies parameter changes by transforming metadata from various sources into a standardized format with consistent data types, structures, and validation rules. Different metadata sources (product labels, descriptions, specifications) are converted to uniform parameters that can be directly compared. This standardization process maintains comprehensive product comparison capabilities while reducing data processing complexity through consistent data representation and automated validation mechanisms.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If manual monitoring of competitor products is performed, then competitive intelligence accuracy is improved, but time consumption and labor requirements increase

Engineering Contradiction:
Improvecompetitive intelligence accuracyVSAvoidtime efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system implements self-service by automatically collecting, standardizing, and analyzing competitor product metadata without requiring manual intervention. The automated system continuously gathers data from multiple sources, applies standardization transformations, and generates competitive intelligence reports. This self-service approach maintains high accuracy through consistent automated processing while dramatically improving time efficiency and reducing labor requirements compared to manual monitoring methods.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4617985A1Method and system for identifying alternative products
Publication Date: 2025.09.17 TATA CONSULTANCY SERVICES LTD
  • EP4617985A1 patent drawingFigure 1
  • EP4617985A1 patent drawingFigure 2
  • EP4617985A1 patent drawingFigure 3

AI summary

This disclosure relates generally to a method and system for identifying alternative products from competitor products having closer similarity to a retailer product. State-of-art methods for alternative product identification based on collaborative filtering often yield inappropriate matches as they do not consider context relevance. Moreover, due to the large size of dataset, such methods require more computation time. While making a comparison of retailer product with the competitor product, a context aware comparison as well as achieving sizable dataset is not yet achieved. The present disclosure addresses these problems through a method of processing metadata of the retailer product and the competitor products to derive feature importance score. The processing results in a filtered data set comprising unique retailer-competitor product pairs. The filtered data is then processed by a machine learning algorithm to identify alternative products based on closest similarity with the retailer product and accordingly ranked.