Claim Complexity Prediction via Supervised-Unsupervised ML Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning approaches often fail to provide accurate predictions when either supervised or unsupervised models are used exclusively, as they either lack predictive complexity or cluster analysis, leading to inaccurate results, especially in scenarios with limited data features.
Innovation Solution
A system that combines the outputs of supervised and unsupervised machine learning models to predict claim complexity by using a multi-branch model for structured and unstructured data, integrating complexity predictions from supervised models with cluster identifications from unsupervised models, and presenting the results on a graphical user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If unsupervised machine learning is selected for claim clustering, then claim grouping by similarity is achieved, but prediction accuracy deteriorates because the given claim may have different complexity from claims in the group
Solution Approach 1:
The patent combines unsupervised learning (for claim clustering and similarity grouping) with supervised learning (for complexity prediction) into an integrated system. The unsupervised model clusters claims by attribute similarity while the supervised model predicts complexity based on historical data from these clusters, merging the strengths of both approaches to achieve accurate predictions with contextual explanation.
2Measurement precision
If supervised machine learning is selected for complexity prediction, then prediction accuracy is improved, but claim clustering by attributes is lost
Solution Approach 1:
The system segments the analysis into two distinct components: an unsupervised learning module that performs claim clustering by attributes and features, and a supervised learning module that performs complexity prediction. This segmentation allows each model to specialize in its strength while the integration layer combines their outputs to provide both accurate predictions and contextual clustering information.
3Measurement precision
If only supervised machine learning is used, then complexity prediction is achieved, but explanation with similar historical claims is not provided
Solution Approach 1:
The unsupervised learning model acts as an intermediary that bridges the supervised prediction model and the explanation generation. It clusters claims by similarity and identifies representative historical claims from these clusters, providing the contextual information needed to explain the supervised model's predictions with similar historical examples.
Data Source
AI summary
A system and a method are disclosed for a tool receiving, from a client device, an indication of a claim. The tool inputs data of the claim into a supervised machine learning model and receiving as output from the supervised machine learning model a complexity of the claim. The tool inputs the data of the claim into an unsupervised machine learning model and receiving as output from the unsupervised machine learning model an identification of a cluster of candidate claims to which the claim belongs. The tool combines complexity and the identification of the cluster into a combined result, and identifies a cell in a matrix corresponding to the combined result. The tool provides, for display at the client device, an identification of the cell, the cell to be emphasized to the user within a display of the matrix.