Entity Similarity Ranking for Illiquid Bond Pricing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for pricing illiquid bonds are inefficient and inaccurate due to the lack of integrated systems for identifying comparable issuers and analyzing nuanced market data, leading to high system resource usage and flawed risk assessments.

Innovation Solution

A system that integrates multiple mechanisms onto a single platform to extract and compare entity information using large language models and Transformer-based Sentence Embedding, generating a similarity ranking to estimate illiquid bond prices by identifying comparable entities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple third-party systems and unintegrated software are used for identifying comparable issuers and analyzing market data, then comprehensive data coverage is achieved, but system resource usage and memory consumption increase significantly

Engineering Contradiction:

Improvedata coverageVSAvoidsystem resource usage

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent consolidates multiple third-party systems and unintegrated software into a single integrated system that combines data collection, entity identification, and similarity analysis functions. This merging reduces system resource overhead while maintaining comprehensive data coverage through unified architecture that efficiently manages data flows between components.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The integrated system performs multiple functions including data collection from various sources, entity identification using machine learning, similarity analysis, and pricing estimation within a single platform. This multi-functionality eliminates the need for separate specialized systems, reducing overall resource consumption while maintaining comprehensive analytical capabilities.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If traditional methods are used for identifying comparable issuers and analyzing market data, then existing systems can be maintained, but pricing accuracy and valuation integrity are compromised

Engineering Contradiction:

Improvevaluation integrityVSAvoidpricing accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces traditional mechanical methods of issuer identification and data analysis with machine learning models and automated similarity analysis algorithms. This substitution enables more precise pricing accuracy through automated entity matching while maintaining valuation integrity through consistent application of analytical criteria across all bonds.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms qualitative assessment parameters into quantitative similarity scores through automated analysis. By changing the parameters from subjective expert judgment to objective algorithmic measurements, the system achieves both higher pricing accuracy and maintained valuation integrity through consistent, reproducible analysis.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If comprehensive entity analysis is performed using multiple data sources, then pricing accuracy improves, but system complexity and integration requirements increase

Engineering Contradiction:

Improvepricing accuracyVSAvoidsystem integration complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the complex analysis system into distinct functional modules: data collection module, entity identification module using machine learning, similarity analysis module, and pricing estimation module. This segmentation manages system complexity by creating manageable components while maintaining comprehensive analysis capabilities for accurate pricing.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The integrated system acts as an intermediary layer that standardizes data from multiple sources before analysis. This intermediary function simplifies integration complexity by providing unified data interfaces and formats, enabling comprehensive entity analysis without requiring direct complex connections between all data sources.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12566768B1Method and system for determining similarities between entities

Publication Date: 2026.03.03 JPMORGAN CHASE BANK NA

AI summary

A method and a system for determining similarities between entities are provided. The method includes: receiving a request to determine an estimate for a first instrument; generating a query to identify corresponding first data sources that contain data about an entity; identifying, using the generated query, the corresponding first data sources from a system of computer networks; filtering the corresponding first data sources in order to determine at least one primary data source; extracting corresponding first information that relates to the respective entity from the at least one primary data source; identifying, using a large language model, corresponding entity-specific information based on the extracted corresponding first information; comparing the entity-specific information of a first entity with entity-specific information for a plurality of entities; and generating a similarity ranking that list each respective entity from among the plurality of entities in relation to the first entity.