Database Abstraction Engine for Fraud Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems require significant manual effort to detect fraudulent activity by connecting customer attributes from different databases, leading to undetected fraudulent activities due to the disparate nature of online activity, demographic, and account data.
Innovation Solution
A database abstraction and data linkage engine that centralizes customer data, receives attributes via an interactive interface, executes queries, dynamically creates attribute datasets, and generates a network of connections to identify potential fraudulent activities, utilizing machine learning for pattern recognition and proactive alerts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual database queries and data manipulation are used to connect customer attributes, then flexibility and control are maintained, but significant manual work is required and fraudulent activity goes undetected
Solution Approach 1:
The system enables self-service automation where the fraud detection engine automatically queries multiple databases, retrieves customer attributes, performs data manipulation, and generates fraud risk scores without requiring manual intervention. The system serves itself by autonomously executing the entire fraud detection workflow from data retrieval to analysis.
Solution Approach 2:
A central data repository acts as an intermediary layer between disparate databases (online activity, demographic, account data) and the fraud detection engine. This intermediary consolidates data from multiple sources into a unified structure, enabling automated querying and analysis while reducing the complexity of manual data integration.
2Loss of information
If data is stored in disparate databases/tables, then data organization and management are simplified, but connections among customer attributes cannot be easily determined
Solution Approach 1:
The system merges data from disparate databases into a unified customer attribute structure within the central data repository. By combining online activity data, demographic data, and account data into a consolidated format with standardized relationships, the system enables comprehensive fraud analysis while preserving the organizational benefits of separate source databases.
Solution Approach 2:
The central data repository provides a universal data access interface that can retrieve and correlate any customer attribute across different data sources. This multi-functional repository serves as a single point of access for all fraud detection queries, eliminating the need for separate complex queries against each individual database while maintaining data integrity.
Data Source
AI summary
The invention relates to database abstraction and data linkage. According to an embodiment of the present invention, the invention takes a variety of attributes (e.g., names, IP address, device identifiers, addresses, phone numbers, account numbers, etc.) and returns the online activity, demographic data, account data and/or other activity, events and data associated with that attribute. The tool may then iterate over each attribute and return a network of connections having multiple degrees of association. The innovative tool may be linked to known bad actor data, and perform automated searches on this data to proactively alert potentially fraudulent activity. The tool may also be developed to add attributes and apply machine learning to the associations to more intelligently describe the returned network. Further, the tool may be developed to describe larger networks having multiple degrees of connections.