Entity Resolution System for Duplicate Party Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Financial institutions face challenges in accurately identifying duplicate entities and linking accounts to prevent money laundering, as existing systems struggle to determine if multiple sets of information refer to the same entity, leading to inaccurate risk scoring and suspicious transaction patterns.
Innovation Solution
A computer-implemented method and system for entity resolution that combines rules-based matching and machine learning algorithms to identify relationships between entities, generating a narrative output that determines the likelihood of entities being the same or related, using a multi-layered approach with a narrative and evaluation channel for comprehensive decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional matching methods are used to identify duplicate entities, then the system is simple to operate, but the accuracy of identifying duplicate entities deteriorates
Solution Approach 1:
The patent combines multiple matching approaches (rules-based matching, machine learning-based matching, and hybrid matching) into a unified entity resolution system. This merging of different techniques allows the system to achieve high accuracy in identifying duplicate entities while managing complexity through a structured multi-layered architecture with narrative and evaluation channels.
Solution Approach 2:
The entity resolution system is segmented into distinct functional components including a narrative channel that generates human-readable explanations and an evaluation channel that assesses matching quality. This segmentation allows each component to specialize in specific tasks, improving overall accuracy while maintaining operational simplicity through clear separation of concerns.
2Measurement precision
If multiple accounts are linked to the same customer, then risk scoring accuracy improves, but the difficulty of detecting and measuring entity relationships increases
Solution Approach 1:
The patent introduces an intermediary entity resolution system that acts as a mediator between raw customer data and risk scoring processes. This intermediary layer uses narrative outputs to explain entity relationships and evaluation outputs to quantify matching confidence, making it easier to detect and measure relationships across multiple accounts while improving risk scoring accuracy.
Solution Approach 2:
The system incorporates feedback mechanisms where evaluation outputs inform and refine the matching process. By continuously evaluating narrative explanations and adjustment suggestions against actual entity relationships, the system improves its ability to detect relationships across multiple accounts, thereby enhancing risk scoring accuracy while managing the complexity of relationship detection.
3Measurement precision
If comprehensive entity information is collected, then the ability to identify duplicate entities improves, but the loss of information processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-processing entity information and pre-computing narrative outputs before final matching decisions are made. This allows the system to have entity relationship explanations ready in advance, reducing the time required for processing during actual duplicate identification while maintaining comprehensive analysis of entity information.
Solution Approach 2:
The system employs partial action by selectively applying different matching strategies based on the specific context and available information. Rather than always performing exhaustive analysis on all entity attributes, the system applies appropriate levels of analysis based on narrative confidence and evaluation results, reducing processing time while maintaining high accuracy in identifying duplicate entities.
Data Source
AI summary
An entity resolution system performs a method of resolving one or more candidate entities based on a data set. The entity resolution system has a rules-based module, a machine learning module, a narrative module, and an evaluation module. The rules-based module compares the first entity features to the second entity features and determines whether a rule identifies a relationship between the first entity and the second entity. The machine learning module rates a similarity of the first entity features and the second entity features. The narrative module generates a narrative output based on one or more of the rules-based module and the machine learning module, the narrative output stating an identified relationship between the first entity and the second entity. The evaluation module determines one or more metrics to apply feedback to the system.