Automated Clustering with Reference-User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated data classification and clustering in large datasets face challenges such as inefficiencies in determining true asset value, incomplete data leading to faulty analysis, and computational complexity, especially in high-dimensional databases where context is difficult to establish, making it hard to achieve accurate risk-adjusted valuations and clustering.
Innovation Solution
A system that identifies and utilizes 'reference-users' with superior insights to modify data processing, update analytics, and influence clustering, leveraging their intuitive pattern recognition to refine data structures and establish context, thereby improving clustering accuracy and relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated data classification and clustering algorithms are used on large datasets, then productivity is improved, but measurement precision deteriorates due to incomplete data and computational complexity
Solution Approach 1:
The patent introduces reference users as intermediaries between automated clustering algorithms and final asset valuations. These users with domain expertise review and adjust cluster assignments, correcting errors that automated systems make due to incomplete data. This intermediary layer preserves the productivity benefits of automation while improving measurement precision through human insight.
Solution Approach 2:
The system implements feedback loops where reference users provide corrections to automated clustering results. Their adjustments are fed back into the system to refine future clustering operations. This continuous feedback mechanism allows the system to learn from human expertise while maintaining high processing throughput, resolving the contradiction between speed and accuracy.
2Measurement precision
If human insights from reference-users are incorporated to improve clustering accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the valuation process into distinct components: automated clustering for initial grouping, reference user review for specific clusters, and algorithmic refinement. This segmentation allows human insights to be applied selectively only where needed rather than throughout the entire process, improving accuracy while limiting the increase in system complexity to manageable levels.
3Reliability
If reference-users are selected and trained to provide superior insights, then reliability is improved, but loss of time increases due to manual review processes
Solution Approach 1:
The patent applies partial action by having reference users review only specific clusters that require human judgment rather than manually reviewing all data points. Automated algorithms handle the majority of clustering operations, while human reviewers focus on borderline or high-stakes cases. This approach maintains high reliability for critical valuations while minimizing time loss through selective human intervention.
Data Source
AI summary
A decision support system and method, which receives user inputs comprising: at least one user criterion, and at least one user input tuning parameter representing user tradeoff preferences for producing an output; and selectively produces an output of tagged data from a clustered database in dependence on the at least one user criterion, the at least one user input tuning parameter, and a distance function; receives at least one reference-user input parameter representing the at least one reference-user's analysis of the tagged data and the corresponding user inputs, to adapt the distance function in accordance with the reference-user inputs as a feedback signal; and clusters the database in dependence on at least the distance function, wherein the reference-user acts to optimize the distance function based on the user inputs and the output, and on at least one reference-user inference.