Clustering Evaluation Platform for Data Attribute Scoring

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data clustering methods face challenges in efficiently generating meaningful cluster solutions from large datasets with numerous variables, as they often produce a vast number of possible clustering results, making it difficult for users to determine the most appropriate grouping, and typically require ad hoc evaluation processes that are inefficient and ineffective.

Innovation Solution

A system that integrates clustering and evaluation by identifying target driver attributes, cluster candidate attributes, and profile attributes, applying clustering algorithms, and calculating scores based on these attributes to generate and refine cluster solutions, allowing users to select relevant variables and cluster sizes, and using machine-learning algorithms to adjust and refine clustering based on previous evaluations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If clustering algorithms are applied to large datasets with numerous variables, then the number of possible cluster solutions increases, but it becomes difficult for users to determine the most appropriate grouping

Engineering Contradiction:

Improvenumber of cluster solutionsVSAvoidevaluation complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements automated evaluation that provides feedback on cluster solution quality using multiple criteria (statistical measures, domain-specific metrics, business objectives). This feedback mechanism allows users to efficiently assess numerous cluster solutions without manual analysis, resolving the contradiction between generating many solutions and evaluating them effectively.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary evaluation layer between clustering algorithms and user interpretation. This intermediary automatically assesses cluster solutions using predefined criteria and presents refined results to users, reducing the complexity burden while maintaining the ability to generate and compare multiple cluster solutions.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If multiple clustering algorithms are used to generate cluster solutions, then more comprehensive results are produced, but ad hoc evaluation processes become inefficient and ineffective

Engineering Contradiction:

Improvecluster solution qualityVSAvoidevaluation efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system changes the parameters of evaluation by introducing multiple automated evaluation criteria (statistical measures, domain-specific metrics, business objectives) instead of relying on ad hoc manual processes. This allows comprehensive evaluation of multiple cluster solutions from different algorithms to be performed efficiently and reliably.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces manual ad hoc evaluation processes with automated computational evaluation systems. This substitution of mechanical human evaluation with automated algorithms dramatically improves evaluation efficiency while maintaining or enhancing solution quality through consistent application of multiple criteria.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If users manually evaluate cluster solutions, then detailed analysis is possible, but the process is time-consuming and difficult to scale

Engineering Contradiction:

Improveevaluation precisionVSAvoidevaluation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements self-service automated evaluation that performs detailed analysis of cluster solutions without requiring manual user intervention. Multiple evaluation criteria are automatically applied, and results are presented ready for interpretation, eliminating time-consuming manual evaluation while maintaining detailed analytical precision.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent performs preliminary automated evaluation of cluster solutions before user review. This preliminary action filters and ranks solutions based on multiple criteria, so users only need to review the most promising results, dramatically reducing evaluation time while preserving detailed analysis capabilities for the final selection.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10102281B2Segmentation discovery, evaluation and implementation platform

Publication Date: 2018.10.16 ACCENTURE GLOBAL SERVICES LTD

AI summary

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described that enable clustering and evaluation of data. A data set is identified for which to evaluate cluster solutions, the data set including a plurality of records each including a plurality of attributes. Different attributes are identified, including target driver attributes, cluster candidate attributes, and profile attributes. One or more clustering algorithms are identified and applied to the data set to generate cluster solutions. Each cluster solution groups records in the data set into different clusters based on the cluster candidate attributes. A score is calculated for each cluster solution based at least on the target driver attributes, the cluster candidate attributes, and the profile attributes. A user interface is generated for presentation to a user showing the generated cluster solution organized according to the calculated score for each cluster solution.