Financial Record Embedding for Automated Transaction Reconciliation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Reconciliation of financial records is difficult due to insufficiently detailed entries in financial systems, making it challenging for both humans and automated systems to identify relevant transaction information, particularly when descriptions lack standardization and specific details such as payer names.

Innovation Solution

A method involving a numerical representation generation model and a transaction attribute prediction model, trained on historical records, to determine attributes like account codes and entity identifiers from financial records, with a user interface for approval and confidence scoring to generate accurate reconciliation records.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated reconciliation systems are used, then productivity is improved, but measurement precision deteriorates due to insufficiently detailed entries in financial records

Engineering Contradiction:

Improvereconciliation speedVSAvoidtransaction attribute identification accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by training the transaction attribute prediction model on historical reconciled financial records before actual reconciliation. This pre-training enables the model to learn patterns and characteristics of accurate reconciliations, improving its ability to accurately identify transaction attributes even when financial record entries are insufficiently detailed.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The transaction attribute prediction model acts as an intermediary between the insufficiently detailed financial records and the reconciliation system. It bridges the gap by inferring and predicting missing transaction attributes based on learned patterns from historical data, enabling automated reconciliation without requiring perfectly detailed source records.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual reconciliation is performed, then measurement precision is improved through human experience, but loss of time increases significantly

Engineering Contradiction:

Improvetransaction attribute identification accuracyVSAvoidreconciliation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the transaction attribute prediction model to automatically identify and determine transaction attributes without requiring manual human intervention for each reconciliation. The model serves itself by using its learned knowledge from historical data to independently process financial records and extract necessary attributes.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system changes parameters by transforming the reconciliation process from manual human analysis to automated model-based prediction. This parameter change shifts the basis of accuracy from human experience to machine learning patterns, while simultaneously reducing time loss through automated processing.

Inventive Principle:

Principle #35Parameter changes

3Ease of operation

If financial records include general descriptions instead of specific details, then ease of operation is improved for financial systems, but difficulty of detecting and measuring increases for reconciliation

Engineering Contradiction:

Improvefinancial record generationVSAvoidtransaction attribute identification

Core Design Contradiction:

Ease of operationVSDifficulty of detecting and measuring

Solution Approach 1:

Instead of requiring financial systems to provide detailed information upfront, the system inverts the approach by using the transaction attribute prediction model to infer and derive specific attributes from general descriptions. The model works backwards from limited information to extract necessary reconciliation attributes.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

The system replaces the mechanical requirement for detailed financial record entries with an intelligent system that can extract meaning from general descriptions. The transaction attribute prediction model substitutes for the need for perfectly detailed source data by using pattern recognition and inference capabilities.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250390960A1Transaction Data Processing Systems and Methods

Publication Date: 2025.12.25 XERO

AI summary

Described embodiments relate to determining a candidate financial record associated with a transaction between a first accounting entity and a second entity, and determining, using a numerical representation generation model, a numerical representation of the candidate financial record, the numerical representation generation model having been trained on a corpus generated from historical transaction records. The method further comprises providing, to a transaction attribute prediction model, the numerical representation of the candidate financial record, the transaction attribute prediction model having been trained using a dataset of previously reconciled financial records, each associated with a respective first transaction attribute; and determining, by the transaction attribute prediction model, at least one first transaction attribute associated with the candidate financial record.