Transaction Attribute Prediction From Sparse Financial Records
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Reconciliation of financial records is challenging due to insufficiently detailed entries in financial systems, making it difficult for both humans and automated systems to identify relevant transaction attributes, particularly in the absence of standardized descriptions.
Innovation Solution
A method involving a numerical representation generation model and a transaction attribute prediction model, trained on historical records, to determine transaction attributes such as account codes and entity identifiers, with a confidence scoring system for accurate reconciliation.
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 financial records
Solution Approach 1:
The patent introduces an intermediary natural language processing system that acts as a mediator between the insufficient financial record entries and the reconciliation requirements. The NLP model generates missing transaction attributes (payer name, payee name, transaction purpose) by interpreting the limited available information, thereby enabling automated reconciliation without sacrificing accuracy.
Solution Approach 2:
The system performs preliminary action by pre-generating transaction attributes using trained NLP models before the actual reconciliation process. The model predicts payer names, payee names, and transaction purposes in advance, so that when reconciliation is needed, the attributes are already prepared and available, eliminating the need for manual analysis during the reconciliation step.
2Measurement precision
If manual reconciliation by accountants is used, then measurement precision is maintained through experience-based judgment, but loss of time increases due to analyzing each entry individually
Solution Approach 1:
The system enables self-service by allowing the financial records to automatically generate their own transaction attributes through the NLP model. Instead of accountants manually analyzing each entry, the records themselves are processed autonomously by the trained model, which extracts and generates the necessary attributes (payer, payee, purpose) without human intervention, thus eliminating time loss while maintaining precision.
3Measurement precision
If financial records include detailed particularised descriptions, then measurement precision improves for identifying transaction attributes, but device complexity increases due to lack of standards in providing descriptions
Solution Approach 1:
The patent applies inversion by reversing the traditional approach: instead of requiring financial records to include detailed standardized descriptions (which would increase complexity), the system takes the existing limited descriptions and uses NLP to generate the detailed attributes. This inverts the problem from 'records must contain all information' to 'model generates information from limited records,' thereby maintaining data simplicity while achieving high measurement precision.
Data Source
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.