Graph-Based AML Platform Reducing False Positives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current anti-money laundering (AML) services rely on rule-based and manual processes, resulting in a high number of false positives and requiring extensive personnel resources, leading to significant capital costs for banks to investigate transactions manually.
Innovation Solution
An AML platform that analyzes information associated with entities involved in money laundering investigations by generating a graph data structure to identify relationships between target and related entities, determining scores, and predicting classes to assess the likelihood of money laundering, thereby reducing false positives and conserving processing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If rule-based and manual processes are used for AML investigations, then thorough analysis can be performed, but the number of false positives increases and extensive personnel resources are required
Solution Approach 1:
The patent introduces an automated analysis system as an intermediary between manual investigation processes. This system uses machine learning models and graph data structures to pre-process and prioritize transaction data, reducing the burden on human investigators while maintaining detection accuracy. The automated system acts as a mediator that filters and ranks suspicious activities before human review.
Solution Approach 2:
The patent replaces manual mechanical review processes with automated computational analysis. Machine learning algorithms and automated scoring systems substitute for human investigators' initial screening work, reducing false positives through consistent application of detection criteria while freeing personnel resources for complex case analysis.
2Measurement precision
If manual investigation processes are used, then detailed analysis is possible, but capital costs for personnel resources increase significantly
Solution Approach 1:
The patent segments the investigation process into automated preliminary analysis and human expert review. The automated system handles data collection, graph generation, and initial scoring, while human personnel focus on analyzing complex cases and making final decisions. This segmentation reduces personnel resource requirements while maintaining analysis depth for critical cases.
Solution Approach 2:
The system performs self-service through automated data processing and analysis. The automated analysis platform independently collects data, generates graph representations, calculates risk scores, and prioritizes cases without requiring extensive human intervention for routine tasks, thereby reducing personnel resource consumption.
3Reliability
If extensive manual investigations are conducted, then thorough detection can be achieved, but processing time and resource consumption increase
Solution Approach 1:
The patent applies preliminary action by automatically generating graph data structures and calculating risk scores before human investigation begins. This pre-processing prioritizes suspicious transactions and prepares analysis frameworks in advance, reducing the time required for manual investigation while maintaining thoroughness through pre-identified key relationships.
Data Source
AI summary
A platform may obtain, for a first set of entities involved in a money laundering investigation, target entity information for a target entity and related entity information for a set of related entities. The platform may analyze the target entity information and the related entity information to identify money laundering candidates. The platform may determine one or more relationships indicating a degree of similarity between the target entity and the one or more related entities. The platform may generate a graph data structure that associates the target entity and the one or more related entities using the one or more relationships. The platform may determine a score for the target entity and one or more scores for the one or more related entities. The platform may provide a recommendation indicating whether the target entity and/or the one or more related entities are likely to be engaging in money laundering.