Behavioral Device Identification for Online Fraud Prevention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods fail to uniquely identify users and their devices for effective authentication in online transactions, leading to challenges in preventing fraud, as they are not robust enough to handle device changes and variations, and are limited by legal restrictions on collecting personally identifiable information.
Innovation Solution
A multi-layer behavioral device identification system that uses smart-agents, real-time profiling, and long-term profiling to create a comprehensive dossier of user device behaviors and configurations, calculating a fraud score in real-time to assess the risk of transactions by analyzing webpage navigation patterns and device attributes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If personal information is collected from users for authentication, then authentication accuracy is improved, but legal compliance deteriorates
Solution Approach 1:
The patent extracts only the necessary behavioral and device configuration data points needed for authentication without collecting personally identifiable information. It takes out the essential identification elements (navigation patterns, device attributes) while leaving out the prohibited PII, thereby achieving authentication accuracy without legal compliance risk.
Solution Approach 2:
The system uses temporary, non-personal device identifiers and behavioral data that are automatically generated and discarded after use. These are not permanent personal records but transient data points that provide authentication capability without creating lasting personal information storage issues.
2Measurement precision
If device configuration data is collected for identification, then device uniqueness is improved, but data collection complexity increases
Solution Approach 1:
The patent employs a universal data collection mechanism that gathers multiple types of information (navigation behavior, device attributes, configuration data) through a single integrated system. This multi-functional approach collects diverse data points needed for unique device identification without requiring separate complex systems for each data type.
Solution Approach 2:
The system leverages data that devices and users naturally generate through their normal operation (navigation patterns, device self-reported attributes). Rather than requiring active user input or complex probing mechanisms, the system collects identification data that is automatically produced during regular device usage.
3Measurement precision
If behavioral patterns are analyzed for fraud detection, then fraud detection accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary analysis of behavioral patterns during the user's normal browsing session before the actual transaction occurs. By pre-establishing baseline behavioral profiles and analyzing navigation patterns in advance, the system prepares fraud detection data beforehand, so that when a transaction occurs, the verification can be completed rapidly without significant delay.
Solution Approach 2:
The patent replaces complex real-time behavioral analysis with pre-computed behavioral profiles and pattern matching algorithms. Instead of performing heavy mechanical analysis during the transaction moment, the system substitutes this with faster comparison operations against previously established behavioral baselines, reducing processing time while maintaining detection accuracy.
Data Source
AI summary
A real-time fraud prevention system enables merchants and commercial organizations on-line to assess and protect themselves from high-risk users. A centralized database is configured to build and store dossiers of user devices and behaviors collected from subscriber websites in real-time. Real, low-risk users have webpage click navigation behaviors that are assumed to be very different than those of fraudsters. Individual user devices are distinguished from others by hundreds of points of user-device configuration data each independently maintains. A client agent provokes user devices to volunteer configuration data when a user visits respective webpages at independent websites. A collection of comprehensive dossiers of user devices is organized by their identifying information, and used calculating a fraud score in real-time. Each corresponding website is thereby assisted in deciding whether to allow a proposed transaction to be concluded with the particular user and their device.