Account Graph Query Merging for Fast Fraud Link Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional fraud detection systems in electronic transaction processing take significant time to identify fraud trends, leading to increased losses and damage to service provider brands, and there is a need for faster and more efficient methods to detect account takeover fraud and other risks.
Innovation Solution
Implementing pairwise graph querying and merging techniques using graph databases to link and analyze account relationships, enabling rapid identification of fraud trends and compliance issues through graph-based data models and machine learning algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If conventional fraud detection systems are used, then fraud detection capability is provided, but response time is significant and computing resources are consumed
Solution Approach 1:
The patent segments the fraud detection process into multiple independent graph query operations that can be executed in parallel. Instead of analyzing all account relationships as a single complex operation, the system divides the analysis into pairwise graph queries between seed accounts and candidate accounts, allowing concurrent processing and significantly reducing overall response time while maintaining comprehensive fraud detection coverage
Solution Approach 2:
The patent implements partial action by limiting graph traversal to a specified maximum number of hops (e.g., 2-5 hops) from seed accounts. This partial exploration approach balances thoroughness with efficiency, examining only the most relevant account relationships within a constrained scope. The system can adjust the traversal depth based on risk assessment, providing sufficient detection capability without exhaustive analysis that would consume excessive resources
2Measurement precision
If comprehensive account analysis is performed, then fraud detection accuracy is improved, but computing resource consumption increases
Solution Approach 1:
The patent performs preliminary actions by pre-computing and storing graph data structures in a graph database before fraud detection queries are executed. Account relationships, transaction patterns, and network structures are prepared in advance and maintained in optimized formats. When fraud detection is needed, the system queries these pre-prepared structures rather than computing relationships from raw data, significantly reducing real-time computing resource consumption while maintaining accurate detection capability
Solution Approach 2:
The patent introduces a graph database as an intermediary layer between raw account data and fraud detection algorithms. This intermediary structure pre-processes and organizes account relationships into efficient queryable formats, acting as a buffer that reduces the computational burden on the fraud detection system. The graph database handles complex relationship computations in advance, allowing the detection algorithms to work with pre-computed structures rather than raw data
Data Source
AI summary
There are provided systems and methods for pairwise graph querying, merging, and computing for account linking. A service provider may provide an account graph system to identify pairwise similarities between different accounts based on shared data that may be identified through one or more linking characteristics. When providing pairwise graph similarities, a service provider may receive a query identifying two or more accounts and/or an account with a parameter for graph exploration and querying.The service provider may utilize connection, link, or relationship graphs, queried and generated using a graph database, to determine pairwise similarities between the designated seed account and one or more selected accounts. The graph may include vertices for different queried data points and edges connecting such queries, where directionality of the edges or other vectors may be used to identify links or hops between accounts for data querying and exploration.