Secondary Card User Identification via Biometric and ML Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional systems and methods fail to identify secondary card users, preventing them from building credit history and leaving accounts vulnerable to fraud, as they cannot distinguish between primary and secondary users based on transaction data alone.
Innovation Solution
A system utilizing machine learning models to analyze transaction information, including biometric data and user preferences, prompts the primary account holder to confirm or deny transactions and recommends designating the secondary user as authorized if the transactions exceed a predetermined threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional systems use account number only for transaction processing, then transaction processing is simple and fast, but the system cannot identify secondary card users and build credit history
Solution Approach 1:
The patent segments the user identification process into multiple components: device identifier detection, biometric data collection, machine learning analysis, and traditional account verification. This segmentation allows the system to accurately identify secondary users without completely redesigning the transaction processing infrastructure.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between the transaction system and user identification. The MLM analyzes device identifiers, biometric data, and transaction patterns to determine secondary user status, acting as a mediator that adds identification capability without directly modifying core transaction processing.
2Reliability
If the system monitors and analyzes transaction data to identify secondary users, then credit history building is enabled, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by collecting device identifiers and biometric data at the point of transaction initiation, before full processing occurs. The machine learning model is pre-trained with transaction patterns, enabling rapid secondary user detection without adding significant processing time to each transaction.
Solution Approach 2:
The system applies partial monitoring by focusing ML analysis only on transactions that exhibit secondary user patterns rather than analyzing every transaction in detail. This selective approach maintains credit history accuracy while reducing overall computational burden and processing time.
3Object-affected harmful factors
If the system implements comprehensive fraud detection through MLM analysis, then fraud risk is reduced, but system complexity and computational requirements increase
Solution Approach 1:
The patent implements feedback mechanisms where the machine learning model continuously learns from transaction outcomes and fraud patterns. The system receives feedback from confirmed secondary users and fraud incidents, refining its detection algorithms over time to improve fraud detection while managing system complexity through adaptive learning.
Solution Approach 2:
The machine learning model serves multiple functions simultaneously: it identifies secondary card users for credit history building, detects potential fraud patterns, and analyzes transaction behavior. This multi-functionality reduces overall system complexity by consolidating multiple security and identification functions into a single unified model.
Data Source
AI summary
A system may receive transaction information associated with a transaction, the transaction information comprising an account number associated with a first user. The system may determine whether the transaction is associated with a second user. Responsive to determining the transaction is associated with the second user, the system may transmit a first prompt to a first user device associated with the first user, the first prompt comprising a request to confirm or deny the transaction. The system may receive, via the first user device, a first user selection confirming the transaction. Responsive to receiving the first user selection, the system may determine whether the transaction exceeds a predetermined threshold. Responsive to determining the transaction exceeds the predetermined threshold, the system may transmit a second prompt to the first user device, the second prompt comprising a recommendation to designate the second user as an authorized user of the account number.