Automated Classification Rule Generation for Financial Decision Platforms

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The current data mining process in the financial field requires multiple human roles and machine analysis, leading to a lengthy process for updating modeling results and applying them to data decision-making, which affects the timeliness and efficiency of data-driven decisions.

Innovation Solution

A computer system performs discretization processing on data samples to convert them into a matrix form, trains the data using a classification method like decision trees, and converts the resulting rule sets into a format recognizable by data decision-making platforms, enabling automated decision-making without human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple human roles and machine analysis are used in the data mining process, then the modeling can be performed with human expertise and control, but the process time and complexity increase significantly

Engineering Contradiction:

Improvemodeling qualityVSAvoidprocess time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automated self-service through the automated rule generation module that automatically generates decision rules from training data without requiring manual intervention from financial modeling experts, rule development teams, or data modeling teams, thereby reducing process time while maintaining modeling quality through algorithmic accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical human-operated process with an automated computer-based system that uses algorithms and machine learning models to perform data mining, rule generation, and decision-making tasks that were previously performed manually by multiple human roles, significantly reducing process time while maintaining or improving reliability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If multiple human roles and machine analysis are used in the data mining process, then the modeling can be performed with human expertise and control, but the process complexity increases

Engineering Contradiction:

Improvemodeling qualityVSAvoidprocess complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent merges multiple separate human roles (financial modeling expert, rule development team, data modeling team, cloud computing team) into a single integrated automated system that performs all functions through computer-based modules, thereby reducing process complexity while maintaining modeling quality through systematic algorithmic processing

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The automated rule generation module serves multiple functions simultaneously - it performs data analysis, generates decision rules, and outputs results in formats compatible with various decision-making platforms, replacing the need for multiple specialized human roles and reducing overall process complexity

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Adaptability or versatility

If manual conversion and mapping processes are used, then the rule sets can be adapted to different platforms, but the automation level and processing speed decrease

Engineering Contradiction:

Improveplatform compatibilityVSAvoidautomation level

Core Design Contradiction:

Adaptability or versatilityVSExtent of automation

Solution Approach 1:

The system automatically adjusts output parameters by generating decision rules in different format types (first format and second format) that are compatible with different decision-making platforms, maintaining platform adaptability while operating fully automatically without manual conversion or mapping processes

Inventive Principle:

Principle #35Parameter changes

4Adaptability or versatility

If manual conversion and mapping processes are used, then the rule sets can be adapted to different platforms, but the processing speed decreases

Engineering Contradiction:

Improveplatform compatibilityVSAvoidprocessing speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent replaces manual conversion and mapping processes with automated computer-based generation of decision rules in multiple formats, significantly increasing processing speed while maintaining platform compatibility through algorithmic output generation rather than human-operated conversion

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9984336B2Classification rule sets creation and application to decision making

Publication Date: 2018.05.29 HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD

AI summary

A data processing method and a computer system. The computer system may perform discretization processing on a data sample to obtain a data sample in a matrix form, train the data sample in the matrix form according to a preset classification method to obtain a classification rule set, and after converting the classification rule set into a classification rule set that can be recognized by a data decision-making platform, provide the classification rule set to the data decision-making platform, so that the data decision-making platform can perform data decision-making according to the classification rule set that is obtained by the computer system by conversion and can be recognized by the data decision-making platform. All the foregoing processes are automatically completed by the computer system, which avoids human participation.