Generative ML Framework for Financial Transaction Test Coverage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional testing methodologies for financial transactions fall short in comprehensively covering diverse scenarios and edge cases, requiring significant human involvement for creating test data and test cases.

Innovation Solution

A generative machine learning framework utilizing large language models (LLMs) to generate diverse and realistic test data and cases for payment use cases, including transaction logs, system specifications, and production incidents, enabling automated user acceptance testing and feedback loops.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional testing methodologies are used, then test cases can be created with existing processes, but comprehensive coverage of diverse scenarios and edge cases is insufficient and requires large human involvement

Engineering Contradiction:

Improvecoverage of diverse scenariosVSAvoidhuman involvement in creating test data

Core Design Contradiction:

Adaptability or versatilityVSExtent of automation

Solution Approach 1:

The system enables automated generation of test data and test cases through ML models that self-service the testing process. The generative ML framework automatically creates diverse test scenarios, edge cases, and test data without requiring manual human intervention, thus achieving both comprehensive coverage and reduced human involvement simultaneously

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes of test case creation with automated ML-based systems. Large language models and generative ML frameworks substitute human analysts, automatically generating test data, test cases, and scenarios through intelligent algorithms rather than human effort

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual creation of test data and test cases is performed, then human expertise can be applied, but productivity and efficiency are reduced due to large human involvement required

Engineering Contradiction:

Improvetest case generation efficiencyVSAvoidmanual creation of test data

Core Design Contradiction:

ProductivityVSExtent of automation

Solution Approach 1:

The ML framework performs self-service by automatically generating test data, test cases, and scenarios without human intervention. The system independently executes the entire testing workflow, from data generation to test execution, dramatically improving productivity while minimizing manual involvement

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent extracts the creative and analytical tasks of test case generation from human operators and transfers them to ML models. The generative models take out the intellectual work of creating diverse test scenarios, leaving humans only with oversight and validation roles

Inventive Principle:

Principle #2Taking out (Extraction)

3Reliability

If comprehensive test coverage is achieved through conventional methods, then all scenarios can be tested, but the process becomes complex and resource-intensive

Engineering Contradiction:

Improverobustness of payment systemsVSAvoidcomplexity of testing process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex manual testing processes with streamlined ML-based automation. The generative ML framework simplifies the testing workflow by automatically handling data generation, test case creation, execution, and analysis, reducing process complexity while maintaining comprehensive coverage for system reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20260010713A1Method and system for a generative machine learning framework generating predictive results

Publication Date: 2026.01.08 JPMORGAN CHASE BANK NA

AI summary

A method and system for a generative machine learning (ML) framework generating predictive results regarding financial transactions. The method includes generating the generative ML framework by connecting: a base layer; a data processing layer; at least one large language model (LLM) layer; a ML processing layer; and an applications layer. The method further includes executing the generative ML framework by: storing and receiving a first data; performing data processing procedures on the first data resulting in a standardized data, wherein the standardized data includes at least one specific case involving the financial transactions. The operations further include parsing the standardized data to generate analytical results with natural language descriptions; inputting, into the ML processing layer, the analytical results; performing predictive modeling of the analytical results to generate the predictive results; transmitting the predictive results; and generating at least one application model based on the predictive results.