Feed-Forward and Feed-Backward Entity Standardization for Noisy Banking Data

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing natural language processing methods struggle to accurately resolve entities from unstructured and often poorly formatted data in banking transactions, such as those found in memo fields, due to reduced grammar and syntax, leading to low accuracy in entity standardization.

Innovation Solution

A computer-implemented method utilizing feed-forward and feed-backward processes, including natural language processing, probabilistic confidence indicators, and entity services, to enhance entity standardization by cross-checking and correcting entity names through merchant metadata, customer feedback, and historical transaction data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional natural language processing components are used to resolve entities from unstructured banking transaction data, then the processing approach is simple and familiar, but the accuracy of entity standardization is low due to reduced grammar and syntax

Engineering Contradiction:

Improveentity standardization accuracyVSAvoidprocessing system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the entity resolution process into multiple specialized components: NLP module for initial processing, entity service for disambiguation, probabilistic confidence indicator for quality assessment, and feed-backward data sources for verification. Each component handles a specific aspect of the complex task, improving overall accuracy while managing complexity through modular design.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary elements including the entity service that mediates between raw NLP output and final entity standardization, and probabilistic confidence indicators that mediate between different data sources. These intermediaries coordinate information flow and resolve conflicts between different processing streams, enabling high accuracy without overwhelming system complexity.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If feed-forward processing alone is used, then the system is simpler and faster, but the accuracy of entity identification is insufficient

Engineering Contradiction:

Improveentity identification accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing data through NLP components before entity resolution, and by using probabilistic confidence indicators to pre-assess data quality. This preliminary processing prepares data in advance, reducing the computational burden during final entity identification and minimizing additional processing time despite the enhanced accuracy approach.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback mechanisms where probabilistic confidence indicators feed back into the entity resolution process, allowing the system to iteratively improve entity identification accuracy. The feed-backward data sources provide feedback loops that verify and correct initial identifications, achieving high accuracy while the feedback is efficiently integrated to minimize processing time delays.

Inventive Principle:

Principle #23Feedback

3Reliability

If probabilistic confidence indicators and feed-backward data sources are integrated, then entity standardization accuracy improves, but the system complexity and data processing requirements increase

Engineering Contradiction:

Improveentity standardization reliabilityVSAvoidsystem architecture complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system achieves reliability through multi-functional components that handle multiple tasks. The entity service simultaneously performs entity disambiguation, data validation, and integration with feed-backward sources. The probabilistic confidence indicator mechanism serves multiple purposes including quality assessment, process optimization, and reliability verification, reducing the need for separate dedicated components for each function.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250225515A1Computer-implemented methods, systems comprising computer-readable media, and electronic devices for feed-forward, feed-backward entity standardization

Publication Date: 2025.07.10 MASTERCARD INT INC

AI summary

Computer-implemented method for entity standardization that includes: inputting unstructured transaction data corresponding to a financial transaction to a natural language processor (NLP) to generate NLP output comprising a portion of the unstructured transaction data; inputting the NLP output to an entity service; inputting a recurring transaction indicator to the entity service; based on the NLP output and the recurring transaction indicator, generating a probabilistic confidence indicator via the entity service, the probabilistic confidence indicator meeting or exceeding a threshold for standardized matching of an entity to the financial transaction; and, based on the probabilistic confidence indicator, associating the entity with one or more of the financial transaction and the NLP output in an entity identification database.