Fraud Detection Network Data Normalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fraud detection mechanisms in digital transactions lack real-time sharing and validation of fraudulent signals across issuers and merchants, making it difficult to effectively scale and combat sophisticated digital fraud.
Innovation Solution
A system and method for intelligent fraud detection that involves receiving and normalizing data from multiple sources, using a trained machine learning model to identify fraud indicators, enriching these indicators with historical data, and notifying subscribing institutions of detected fraud events, enabling real-time fraud management and mitigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fraud detection mechanisms are designed to manage individualized risks separately, then each solution can be optimized for specific risk types, but real-time sharing and validation of fraudulent signals across issuers and merchants cannot be achieved
Solution Approach 1:
The patent combines individualized fraud detection systems from multiple issuers and merchants into a unified networked system. The fraud detection network receives data from multiple sources, normalizes it to a common format, and enables real-time sharing of fraudulent signals across all participants, allowing collective intelligence to improve detection accuracy while maintaining individual risk management capabilities
Solution Approach 2:
The system creates a universal data normalization layer that handles multiple types of fraud data from different sources (issuers, merchants, third parties) using a single standardized framework. The normalized data set can accommodate various fraud indicators and risk types while maintaining consistent processing rules, enabling the system to serve multiple functions across different participants
2Reliability
If data from multiple sources is collected and normalized for comprehensive fraud detection, then fraud detection capability is improved, but data processing complexity and computational requirements increase
Solution Approach 1:
The system transforms heterogeneous fraud data from multiple sources into a standardized parameter format through normalization. By converting diverse data types into a common structure with standardized fields and data formats, the system reduces processing complexity while maintaining comprehensive fraud detection capabilities across all data sources
3Speed
If real-time fraud detection and notification is implemented across the network, then response time to fraud events is improved, but system resource consumption and operational complexity increase
Solution Approach 1:
The system performs data normalization and creates the normalized data set in advance, before fraud detection is needed. This preliminary processing organizes and standardizes data from multiple sources upfront, so that when fraud events occur, the system can quickly query and analyze pre-processed data without performing complex real-time normalization, thus improving response speed while maintaining operational efficiency
Data Source
AI summary
A method for fraud detection and management may include a fraud detection computer program: receiving data from a plurality of sources, each data associated with a unique identifier; normalizing the data; modeling the normalized data with a trained machine learning data model; extracting features or attributes from the modeled data; generating one or more sets of weights for the features or attributes; identifying a subset of the features or attributes indicative of fraud based on the weights; enriching the subset of the features or attributes; detecting fraud based on the enriched subset of the features or attributes; and notifying one or more subscribing institutions of a fraud event for the detected fraud based on the validated subset of the features or attributes.