Electronic Network Fraud Detection Through Consortium Data Sharing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic networks face challenges in effectively detecting fraudulent transactions due to limited data sharing and evaluation capabilities among network actors, particularly in card-not-present transactions, which increases the susceptibility to fraud.
Innovation Solution
A system and method that utilizes a trust knowledge broker to facilitate additional data sharing between merchants and banks through a cloud data pipe and anti-fraud consortium, enabling enhanced fraud detection by providing transaction contextual data and using a consortium trust-base for fraud scoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If parties attempt to mitigate fraud based on limited available information, then fraud detection capability is maintained within individual party constraints, but the overall fraud detection effectiveness deteriorates due to insufficient data scope
Solution Approach 1:
The patent merges information from multiple parties (merchants, banks, third-party providers) into a unified fraud detection system. The trust knowledge broker consolidates transaction data, device information, location data, and other relevant information from diverse sources to create a comprehensive fraud assessment, resolving the contradiction by combining limited individual data sets into a complete multi-source information pool.
Solution Approach 2:
The trust knowledge broker acts as an intermediary that facilitates information sharing between merchants and banks. It receives requests from either party, queries the consortium trust-base for relevant fraud information, and returns comprehensive fraud scores and assessments. This intermediary mechanism enables parties to access information beyond their own data holdings without requiring direct access to each other's systems.
2Reliability
If additional data sharing is implemented between merchants and banks, then fraud detection capability is improved, but system complexity increases due to multiple data channels and coordination requirements
Solution Approach 1:
The trust knowledge broker is designed as a universal system that serves multiple functions: it handles fraud detection requests from both merchants and banks, maintains the consortium trust-base, manages data from multiple third-party providers, and provides standardized fraud scoring. This multi-functional design reduces overall system complexity by consolidating what would otherwise require separate systems for each function.
Solution Approach 2:
The trust knowledge broker simplifies system complexity by acting as a single intermediary point that all parties interact with. Instead of requiring merchants and banks to establish direct data sharing channels between themselves, all information requests flow through the broker, which manages the complexity of coordinating multiple data sources and parties behind a unified interface.
3Measurement precision
If real-time fraud evaluation is performed using comprehensive transaction data, then fraud detection accuracy is improved, but processing time increases due to extensive data analysis requirements
Solution Approach 1:
The system performs preliminary actions by maintaining the consortium trust-base with pre-aggregated fraud information from multiple sources before actual transaction evaluation is needed. Device fingerprints, location patterns, and fraud indicators are pre-processed and stored in the trust-base, allowing the trust knowledge broker to quickly retrieve and evaluate relevant information during real-time transaction assessment without performing exhaustive analysis from scratch.
Data Source
AI summary
This disclosure relates to systems and methods of risk detection in an electronic network. The method may include receiving a first portion of session context information for an interaction of an individual over a limited bandwidth network, the first portion including a session identifier for the interaction. The method may include retrieving a second portion of session context information for the interaction over a cloud data pipe using the session identifier, in response to receiving the first portion. The method may include accessing, a data structure representing connected knowledge of the individual. The method may include receiving, via a distributed system, security reputation data including aggregated information from a plurality of members. The method may include analyzing the session context information using the security reputation. The method may include generating a security risk score for the interaction based on the session context information, data structure, and the security reputation data.