Device-Correlation Fraud Detection with Real-Time Confirmation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing fraud detection systems in financial transactions lack real-time verification and user-generated information, leading to high false positive rates and inconveniences, especially in cross-border transactions, and do not effectively utilize location and behavioral data for authentication.
Innovation Solution
A fraud detection system that authenticates transactions by analyzing user-specific information, including location and behavioral data, using dynamic weighting to determine correlation between device characteristics, and verifies transactions through real-time confirmation from associated devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If aggressive fraud detection strategies are implemented, then fraud detection capability is improved, but false positive rate increases causing inconveniences to cardholders and merchants
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing device characteristics, location data, and behavioral patterns before the transaction occurs. This advance preparation enables more accurate real-time fraud detection without requiring aggressive post-transaction verification, thereby reducing false positives while maintaining detection capability.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring transaction outcomes and user responses to refine its fraud detection algorithms. This feedback loop allows the system to learn from false positives and adjust its detection thresholds, improving accuracy over time while maintaining user convenience.
2Measurement precision
If real-time verification is implemented across all ecosystem players, then fraud detection accuracy is improved, but system complexity increases
Solution Approach 1:
The system achieves universality by creating a standardized verification protocol that can be implemented by any ecosystem player (banks, merchants, payment processors). This multi-functional approach allows different entities to participate in real-time verification without requiring complex custom integrations, thereby improving fraud detection accuracy while controlling system complexity.
Solution Approach 2:
The system introduces an intermediary verification layer that coordinates between different ecosystem players. This mediator component manages the complexity of multi-party verification by standardizing communication protocols and data formats, enabling accurate real-time fraud detection without requiring direct complex interactions between all participants.
3Measurement precision
If user-generated information and real-time status data are integrated, then fraud detection precision is improved, but information processing requirements increase
Solution Approach 1:
The system extracts and prioritizes only the most critical user-generated information and real-time status data relevant to fraud detection. By selectively extracting key indicators (such as unusual location changes, abnormal transaction patterns) rather than processing all available data, the system improves detection precision while controlling information processing requirements.
Solution Approach 2:
The system applies local quality by differentiating the level of analysis applied to different data sources and transaction types. High-value or suspicious transactions receive more intensive processing of user-generated information, while routine transactions use streamlined verification. This targeted approach improves overall detection precision without uniformly increasing processing requirements across all transactions.
Data Source
AI summary
The present invention provides a method of authenticating a transaction, the method having: responsive to receiving a request for authenticating a transaction involving a first device and including first device information defining at least one first device characteristic of the first device, obtaining second device information defining at least one second device characteristic of a second device associated with the transaction; determining a level of correlation between the first device information and the second device information; and authenticating the transaction based on the level of correlation between the first device information and the second device information, wherein the transaction is authenticated when the level of correlation between the first device information and the second device information is above a pre-determined threshold.