Merchant Logo Similarity Filtering for Accessible Account Authentication
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing authentication systems face challenges in achieving high security while minimizing authentication failures due to similarities in merchant names or logos, particularly for users with disabilities or language barriers, leading to confusion and potential unauthorized access.
Innovation Solution
A computing device processes merchant names and logos using natural language processing and machine learning models to identify similarities, excluding confusing merchants from authentication questions, thereby enhancing security and accessibility for users with disabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If authentication questions are generated based on real transactions with merchants having similar names or logos, then authentication security is improved, but authentication failure rate increases due to user confusion
Solution Approach 1:
The system performs preliminary analysis of merchant names and logos before generating authentication questions. It compares potential questions against a database of similar merchants and pre-filteres out questions that would cause confusion, thereby preventing authentication failures before they occur
Solution Approach 2:
The system introduces an intermediary verification step between transaction data and authentication question generation. This intermediary layer analyzes merchant similarity metrics and mediates the selection process to ensure questions are both secure and distinguishable for users
2Productivity
If authentication questions include all merchants from transaction history, then authentication thoroughness is improved, but user confusion increases due to similar merchant names and logos
Solution Approach 1:
The system extracts and removes problematic merchant entries from the authentication question pool. By identifying merchants with similar names or logos that could cause confusion, it selectively excludes them while maintaining comprehensive coverage of legitimate transactions
Solution Approach 2:
The system applies different quality standards to different merchant entries. Rather than treating all merchants uniformly, it analyzes individual merchant characteristics (name similarity, logo similarity) and applies selective filtering based on local quality metrics to minimize confusion while maintaining authenticity
3Device complexity
If the system uses basic merchant name matching, then system complexity is reduced, but authentication accuracy decreases due to phonetic and visual similarities
Solution Approach 1:
The system implements a multi-functional merchant similarity detection mechanism that handles multiple types of similarity (phonetic, visual, spelling) through a unified framework. This universal approach improves accuracy without proportionally increasing complexity by leveraging existing NLP and image processing capabilities
Data Source
AI summary
Methods, systems, and apparatuses are described herein for improving computer authentication processes through the exclusion of certain merchants that may cause confusion. Indications of a plurality of different merchants, including merchant logos may be received. The indications may be processed to identify at least one similarity between a first merchant and a second merchant. A request for access to an account associated with a user and transaction data corresponding to the account may be received. Based on the similarity between the first merchant and the second merchant, at least one transaction corresponding to the first merchant may be removed to generate processed transaction record. An authentication question may be generated and a candidate response to the authentication question may be received. Based on the candidate response, access to the account may be provided.