Category-Bound Virtual Card Identifiers for Fraud Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual card number systems struggle with managing merchant-bound VCNs, leading to difficulties in maintaining security and preventing fraud due to the inability to control where VCNs are used, especially in online transactions.
Innovation Solution
Implementing a machine learning-based system that identifies merchant categories for binding unique schema-specific identifiers (VCNs) using an entity category determining engine, allowing secure and controlled usage based on predicted categories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If virtual card numbers are made universally usable without binding to specific merchants, then ease of operation is improved, but security and fraud prevention deteriorate
Solution Approach 1:
The patent applies local quality by creating different types of VCNs with different binding characteristics. Some VCNs are bound to specific merchants while others are bound to merchant categories, allowing the system to provide both universal usability and security based on the specific use case. The machine learning engine determines the appropriate binding level for each VCN based on user behavior patterns.
Solution Approach 2:
The system dynamically adjusts VCN binding based on user behavior. The machine learning engine continuously monitors transaction patterns and automatically updates category bindings, allowing VCNs to evolve from unbound to category-bound based on observed usage. This dynamic approach maintains ease of use while progressively improving security.
2Reliability
If virtual card numbers are bound to specific merchants, then security is improved, but ease of operation deteriorates
Solution Approach 1:
The patent implements universality by binding VCNs to merchant categories rather than individual merchants. A single category-bound VCN can be used across multiple merchants within the same category, providing both security through binding and ease of use through broad applicability. This multi-functional approach eliminates the need for multiple merchant-specific VCNs.
Solution Approach 2:
The system creates multiple VCNs that are copies with the same category binding, allowing users to have backup virtual card numbers for the same merchant category. These copied VCNs maintain the same security properties while providing operational flexibility if one VCN becomes compromised or expires.
3Reliability
If machine learning engine is used to predict merchant categories, then security is improved through accurate binding, but device complexity increases
Solution Approach 1:
The machine learning engine operates autonomously, automatically monitoring user transactions, identifying merchant categories, and binding VCNs without requiring manual user input. The system serves itself by continuously training on new data and automatically adjusting bindings, reducing the operational burden while maintaining high security.
Solution Approach 2:
The system implements feedback loops where transaction data is continuously fed back to the machine learning engine, which then adjusts category bindings based on observed patterns. This feedback mechanism allows the system to self-optimize and improve security over time while adapting to changing user behaviors and new merchant types.
Data Source
AI summary
A method including receiving activity data related to a first activity utilizing an unbound schema-specific identifier; training a machine learning engine based on at least one input to obtain a trained machine learning engine that is trained to identify a category associated with the entity; where the at least one input includes: an entity data feature vector, a historical user activity data feature vector, and/or a historical user schema-specific identifier data feature vector; predicting via the trained machine learning engine, a category associated with the first activity; binding the unbound schema-specific identifier to the category to generate a category bound schema-specific identifier; receiving a request to perform a second activity using the bound schema-specific identifier; determining if a second entity associated with the request to perform the second activity is associated with the category; performing one of: approving or denying the request to perform the second activity.