Financial Record Embeddings for Accurate Transaction Reconciliation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Reconciliation of financial records is challenging due to insufficiently detailed entries in bank statements, making it difficult for both humans and automated systems to identify relevant transaction information, particularly when descriptions lack standardization and specific entity names.
Innovation Solution
A method involving a numerical representation generation model and a transaction attribute prediction model, trained on historical records, to determine attributes such as account codes and entity identifiers from financial records, with a user interface for approval and confidence scoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated reconciliation systems are used, then productivity is improved, but measurement precision deteriorates due to insufficiently detailed entries in bank statements
Solution Approach 1:
The patent introduces numerical representations as an intermediary between the bank statement entries and the reconciliation system. These numerical representations encode transaction attributes in a standardized format that machines can process accurately, bridging the gap between insufficient textual descriptions and precise automated reconciliation requirements
Solution Approach 2:
The system transforms transaction attributes from their original textual form into numerical parameters through trained prediction models. This parameter transformation enables automated systems to process and compare transaction data with precise mathematical operations, improving measurement precision while maintaining high productivity
2Measurement precision
If manual reconciliation is performed, then measurement precision is improved through human experience, but loss of time increases significantly
Solution Approach 1:
The system performs preliminary actions by pre-training prediction models on historical transaction data before actual reconciliation occurs. This preliminary training enables the automated system to quickly and accurately identify transaction attributes during the actual reconciliation process, achieving both speed and precision
Solution Approach 2:
The patent replaces the mechanical human analysis process with an automated machine learning system. The trained prediction models substitute for human experience and judgment, enabling automated identification of transaction attributes with both high speed and maintained precision through learned patterns from historical data
3Measurement precision
If detailed transaction descriptions are provided, then measurement precision is improved, but device complexity increases due to lack of standardization
Solution Approach 1:
The patent creates a universal numerical representation framework that can handle various types of transaction descriptions from different banks and formats. This universal system processes diverse input formats through standardized prediction models, achieving precise attribute determination without increasing system complexity through standardization
Data Source
AI summary
A method comprises: determining a candidate financial record associated with a transaction between a first accounting entity and a second entity; 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; 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; determining, by the transaction attribute prediction model, at least one first transaction attribute associated with the candidate financial record.