Machine Learning Transaction Settlement Rule Generation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The current trade deduction settlement process in B2B transactions is manual, error-prone, and time-intensive due to the reliance on static heuristic rules, requiring significant human intervention and failing to adapt to changing data formats and patterns, leading to inefficiencies in matching deductions to promotions.

Innovation Solution

The implementation of AI-based machine learning to automatically identify and generate transaction settlement rules by analyzing historical resolved pairs, enabling the automation of deduction-promotion matching through confidence-score-based auto-matching and recommendations for analysts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If manual heuristic rules are used for trade deduction settlement, then the process can be implemented with simple logic, but it becomes time-intensive and error-prone

Engineering Contradiction:

Improveease of implementing settlement logicVSAvoidsettlement processing speed

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The patent replaces manual heuristic rule-based processing with an automated machine learning system that uses neural networks to analyze historical data and generate settlement recommendations. This substitution of mechanical manual processes with automated AI-based systems resolves the contradiction by maintaining ease of implementation while dramatically improving processing speed and productivity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Device complexity

If static heuristic rules are used for deduction settlement, then the system structure remains simple, but the rules become outdated over time

Engineering Contradiction:

Improvesystem structure simplicityVSAvoidadaptability to changing data formats

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic system where machine learning models continuously learn from historical resolved pairs and automatically update settlement recommendations. This dynamic adaptation mechanism allows the system to evolve with changing data formats and business logic without requiring manual rule updates, resolving the contradiction between system simplicity and adaptability.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs self-learning and self-updating by automatically analyzing historical resolved deduction-promotion pairs to generate improved settlement rules. This self-service capability enables the system to adapt to changing conditions autonomously, maintaining relevance over time without external intervention.

Inventive Principle:

Principle #25Self-service

3Ease of manufacture

If manual rule creation is used, then the initial setup is straightforward, but it requires significant human intervention and is error-prone

Engineering Contradiction:

Improveease of establishing settlement rulesVSAvoidaccuracy of deduction-promotion matching

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent uses machine learning to automatically copy and learn from historical resolved deduction-promotion pairs to generate new settlement recommendations. This copying mechanism allows the system to replicate successful matching patterns from the past, improving reliability and reducing human error while maintaining ease of initial setup through automated rule generation.

Inventive Principle:

Principle #26Copying

4Productivity

If automated machine learning is implemented, then auto-matching rates increase and manual labor reduces, but the system complexity increases

Engineering Contradiction:

Improvesettlement processing efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements a universal machine learning framework that handles multiple functions including learning from historical data, generating settlement recommendations, and adapting to changing patterns. This multi-functional approach consolidates complexity into a single unified system, improving productivity while managing overall system complexity through functional integration.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11100409B2Machine learning assisted transaction component settlement

Publication Date: 2021.08.24 HIGHRADIUS CORP

AI summary

A system generates trade deduction settlement rules and associated confidence scores independent of buyer specifications. A machine learning equipped rewards based method performed by the system analyzes historically matched deductions and promotions to understand patterns. Penalties are applied to outdated rules, and recent trends are promoted through rewards. All available deduction-promotion combinations may be analyzed in batches for a given time period at each pair level within an artificial intelligence model of the method. A rules selector selects the most recurring patterns along those combinations based upon definable thresholds. The system finds hidden patterns to provide suggestions for trade deduction settlement. The system further captures the rules and evolves the rules over time.