Transaction-Based Authentication Excluding Fraudulent Merchants
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transaction-based authentication methods are frustrated by including fraudulent transactions that users do not remember or are confused by, leading to inefficiencies and security risks.
Innovation Solution
A computing device uses a machine learning model to determine a confidence threshold for fraudulent transactions, generating modified merchant choices for authentication questions, excluding potentially fraudulent transactions, and tailoring the questions to improve user accessibility and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If transaction-based authentication questions include all transactions from user history, then the authentication can be based on real user activity, but fraudulent transactions cause user confusion and reduce authentication reliability
Solution Approach 1:
The patent extracts and removes potentially fraudulent transactions from the authentication question pool. The system identifies transactions with fraudulent confidence scores above a threshold and excludes them from being presented to users, thereby eliminating the source of confusion while maintaining authentication reliability.
Solution Approach 2:
The system uses fraud detection algorithms that provide feedback scores indicating the likelihood of each transaction being fraudulent. This feedback mechanism enables the system to dynamically adjust which transactions are included in authentication questions, improving both reliability and user experience.
2Reliability
If the system uses fraud detection algorithms to identify fraudulent transactions, then security is improved, but the complexity of the authentication system increases
Solution Approach 1:
The patent introduces an intermediary fraud detection algorithm layer between the transaction database and the authentication question generator. This intermediary component analyzes transactions and assigns confidence scores, enabling the system to maintain security without requiring complex changes to the core authentication logic.
Solution Approach 2:
The system segments the authentication process into distinct components: transaction retrieval, fraud scoring, threshold evaluation, and question generation. This segmentation allows each component to be optimized independently, reducing overall system complexity while maintaining security.
3Ease of operation
If the system excludes transactions with high fraudulent confidence scores, then user confusion is reduced, but potentially valid transactions may be excluded
Solution Approach 1:
The system uses a configurable confidence score threshold parameter that can be adjusted to balance between user experience and authentication accuracy. By changing this parameter, the system can adapt to different security requirements and transaction types, optimizing the exclusion criteria dynamically.
Data Source
AI summary
Methods, systems, and apparatuses are described herein for improving computer authentication processes through excluding fraudulent transactions in transaction-based authentication. A computing device may receive a request for access to an account from a user. The computing device may provide transaction data to a machine learning model. The computing device may receive data indicating a confidence threshold associated with the user from the machine learning model. The computing device may generate a modified set of merchant choices for the user by excluding merchants related to potentially fraudulent transactions within a predetermined time period. An authentication question may be generated, and access to the account may be provided based on a response to the authentication question.