Shared Account Decomposition for Accurate Transaction Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing online service providers face challenges in accurately authenticating multiple users sharing a single account due to inconsistent transaction behaviors, leading to potential fraudulent transactions or legitimate requests being denied.
Innovation Solution
An account decomposition system that analyzes past transactions using machine learning models to identify distinct user profiles based on device attributes and transaction patterns, employing constrained clustering to group transactions into clusters associated with specific users, thereby enhancing authentication accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If transaction behavior authentication is used for user accounts, then authentication automation is improved, but authentication accuracy deteriorates when multiple users share the account
Solution Approach 1:
The patent segments a shared user account into multiple distinct user profiles by analyzing transaction behavior patterns. Each profile represents a different user with unique characteristics, allowing the system to automatically identify which profile initiated a transaction while maintaining high authentication accuracy despite multiple users sharing the account.
2Adaptability or versatility
If a single user account is shared by multiple users, then account versatility is improved, but transaction processing reliability deteriorates
Solution Approach 1:
The system segments transaction histories into distinct clusters corresponding to different users, enabling reliable transaction processing by identifying the specific user profile behind each transaction request while maintaining the convenience of shared account access.
Solution Approach 2:
The patent applies local quality by creating user-specific transaction patterns and behavior profiles for different individuals sharing the account. Each user profile has its own characteristic transaction attributes, allowing the system to process transactions reliably by matching them to the appropriate local user profile rather than treating the account as a single homogeneous entity.
3Quantity of substance
If transaction patterns are derived from mixed user behaviors, then data quantity is improved, but pattern accuracy deteriorates
Solution Approach 1:
The system segments the mixed transaction data into distinct clusters, each representing a specific user's behavior patterns. This segmentation preserves the beneficial quantity of transaction data while improving pattern accuracy by ensuring that patterns are derived from homogeneous user behaviors rather than mixed behaviors of multiple users.
Solution Approach 2:
The patent uses clustering algorithms to partially process the transaction data by grouping it into distinct user profiles before deriving patterns. This partial processing approach ensures that patterns are accurate for each user segment while still utilizing the full quantity of available transaction data across all users.
Data Source
AI summary
Methods and systems are presented for identifying different users who share a user account with an online service provider and dynamically processing transactions for the user account differently based on which user initiates the transaction request. In some embodiments, an account decomposition system may decompose the user account into distinct users who share the user account. The account decomposition system may identify different users who are sharing a user account by analyzing past transactions associated with the user account and different user devices that were used to conduct the past transactions. The account decomposition system may determine different user profiles for the different users, and may use the different user profiles to process incoming transaction requests initiated by different users of the user account.