Entity Matching Using Financial Data Distance Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing business software systems face challenges in accurately determining whether multiple records represent the same entity due to inconsistencies in non-financial data entries, such as company names and addresses, leading to incomplete or inconsistent data and potential misidentification of companies across different software applications.
Innovation Solution
A system that determines the likelihood of two entities being the same by analyzing financial data, including transactional data, and non-financial data, using distance metrics and weighting to calculate a likelihood score, which can then alter records accordingly based on the determined similarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multiple users enter profile data manually, then data entry flexibility is improved, but data consistency deteriorates
Solution Approach 1:
The system performs self-service by automatically comparing entity records and determining likelihood of sameness without requiring manual intervention from users. The processor autonomously analyzes financial and non-financial data to identify duplicate entities, eliminating the need for users to manually ensure data consistency while preserving their freedom to enter data in various formats.
2Speed
If software providers use basic string comparison for entity identification, then processing speed is improved, but identification accuracy deteriorates
Solution Approach 1:
The system changes the parameters used for entity comparison from simple string matching to multiple data dimensions including financial data (transactions, vendors, customers) and non-financial data (addresses, phone numbers). By analyzing multiple parameters simultaneously, the system achieves higher identification accuracy while maintaining processing efficiency through automated computational methods.
Solution Approach 2:
The entity identification system combines multiple types of data (financial and non-financial) to create a composite profile for each entity. This composite approach, analogous to composite materials in engineering, leverages the strengths of different data types to achieve more accurate entity matching than any single data type could provide alone.
3Measurement precision
If comprehensive financial and non-financial data is collected, then entity identification accuracy is improved, but data processing complexity deteriorates
Solution Approach 1:
The system segments the complex data processing task into distinct components: collecting financial data, collecting non-financial data, comparing entities across multiple dimensions, and determining likelihood of sameness. By dividing the overall process into manageable segments, the system handles comprehensive data without being overwhelmed by complexity, as each segment can be processed independently and systematically.
Data Source
AI summary
The disclosed embodiments provide a system that determines a likelihood that a first entity and a second entity are the same entity. During operation, the system obtains financial data related to the first entity and obtains financial data related to the second entity. Next, the system determines the likelihood that the first entity and the second entity are the same entity based on the relationship between the financial data for the first entity and the financial data for the second entity. Then, the system alters a record related to the first entity or the second entity based on the likelihood.