Synthetic Identity Detection via Entity Link Inconsistency Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems are ineffective in detecting synthetic online identities linked to fraud-facilitating accounts, allowing fraudulent activities to go undetected due to lack of complete match in personally identifiable information and reliance on indicators of authenticity.
Innovation Solution
A fraud detection computing system that analyzes relationships between primary and secondary entities by generating entity links and using machine learning models to identify inconsistencies in attributes such as physical addresses and family names, providing real-time fraud warnings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing systems rely on indicators of authenticity and complete match in personally identifiable information, then they can process transactions efficiently, but they fail to detect synthetic identities that use fake documentation
Solution Approach 1:
The system segments the fraud detection process into multiple independent components: entity resolution service that creates unique identifiers, relationship graph builder that maps connections, and fraud detection engine that analyzes patterns. This segmentation allows each component to specialize in one aspect of detection while maintaining overall system efficiency.
Solution Approach 2:
The patent introduces an intermediary entity resolution service that acts as a mediator between transaction processing systems and fraud detection systems. This service creates standardized unique identifiers and relationship representations that enable sophisticated fraud detection without requiring changes to existing transaction processing infrastructure.
2Productivity
If systems use automated computing to service loan applications, then processing speed increases, but synthetic identities can perform transactions without appearing suspicious
Solution Approach 1:
The system performs preliminary actions by building relationship graphs and entity profiles before fraud detection is needed. The entity resolution service pre-processes information to create unique identifiers, and the relationship graph builder pre-maps connections between entities. When a transaction occurs, this pre-computed information enables rapid fraud assessment without slowing down processing.
Solution Approach 2:
The system implements feedback mechanisms where fraud detection results are fed back into the relationship graph and entity profiles. Detected fraud patterns update the relationship graph to improve future detection, creating a learning system that becomes more accurate over time while maintaining fast processing speeds.
3Object-affected harmful factors
If synthetic identities provide anonymity through fake documentation, then fraudulent activities can be concealed, but relationship patterns between entities remain detectable
Solution Approach 1:
Instead of verifying identity through traditional documentation checks (one dimension), the system moves to another dimension by analyzing relationship patterns between entities. The relationship graph captures connections across multiple dimensions (shared addresses, phones, devices, transaction patterns), making it impossible for synthetic identities to maintain anonymity without revealing inconsistent relationship patterns.
Data Source
AI summary
In some aspects, a computing system can detect synthetic identities based on attributes associated with online entities. The computing system can generate entity links between primary entity objects and a secondary entity object. The secondary entity object identifies a target consumer as a secondary entity for accounts identified by the primary entity objects. Attributes of the secondary entity object and attributes of the primary entity objects can be calculated and compared to determine an inconsistency between a combination of a name attribute value and an address attribute value of the secondary entity object as compared to the primary entity objects. A fraud warning indicating that the target consumer is likely to be a synthetic identity can be generated based on the inconsistency and other attributes of the target consumer, such as an inquiries attribute, a terminations attribute, a duration attribute, and so on.