Trace-Based Financial Record Verification Against External Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing auditing methods rely on random sampling, which can miss problematic entries in financial records, undermining the trustworthiness of audited financial statements.
Innovation Solution
A trace-based data verification process that analyzes associations across multiple financial records and compares them to independently-sourced external data to validate entries, using machine learning techniques to identify traces and determine confidence scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If random sampling is used to verify financial records, then the auditing process is efficient and quick, but the reliability of detection is reduced because problematic entries may remain undetected
Solution Approach 1:
The patent replaces the mechanical random sampling method with an AI-based system that uses machine learning models, natural language processing, and automated trace analysis to systematically examine financial records. This substitution enables comprehensive verification of all entries rather than relying on random samples, thereby improving detection reliability while maintaining auditing efficiency through automation.
Solution Approach 2:
The patent introduces an AI-based intermediary system that acts as a mediator between auditors and financial records. This intermediary uses trained machine learning models to analyze traces, identify anomalies, and generate verification results, thereby enhancing the reliability of detection without requiring manual examination of every entry, thus maintaining productivity.
2Reliability
If comprehensive verification of all entries is performed, then the trustworthiness of audited records increases, but the time and resources required for auditing increase significantly
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models on historical financial data and anomaly patterns before actual auditing. This pre-training enables the system to quickly identify suspicious traces and prioritize verification efforts, allowing comprehensive verification of critical entries while reducing time spent on obviously valid records, thus balancing trustworthiness with auditing time.
Solution Approach 2:
The patent replaces manual comprehensive verification with an automated AI system that uses machine learning models to rapidly analyze financial records. The system can process and verify all entries systematically without the time constraints of manual auditing, achieving both high trustworthiness through complete verification and efficiency through automation.
3Measurement precision
If trace-based verification using independently sourced data is implemented, then the precision of verification improves, but the device complexity increases due to multiple data sources and analysis layers
Solution Approach 1:
The patent applies segmentation by dividing the verification system into distinct modular components: data collection modules for different sources, trace analysis modules using specific machine learning algorithms, verification modules, and reporting modules. This segmentation allows each component to be independently developed, tested, and maintained, reducing the perceived complexity while enabling high verification precision through specialized analysis of each data source.
Solution Approach 2:
The patent implements universality by designing a multi-functional AI platform that can handle multiple data sources (bank records, customer data, supplier data), various analysis types (trace verification, anomaly detection, pattern recognition), and different output formats. This universal system reduces complexity by consolidating multiple specialized tools into a single integrated platform that performs all verification functions.
Data Source
AI summary
The present disclosure is directed to transforming a data set of discrete records, tracing unrelated entries across the records, and verifying the traces using independently-sourced external data. In one aspect, a system includes memory and one or more processors configured to execute the computer-readable instructions to receive a first set of data, the first data set including multiple discrete financial records of an entity; apply a set of logics to the first data set to identify a plurality of traces, each of the plurality of traces associating discrete entries across one or more of the multiple financial records; performing a verification process to verify the plurality of traces against a second data set for the entity, the second data set being independently sourced from a third party entity to yield a verification result; and prepare an output of the verification result to be presented on a display.