Behavioral Biometric Age Prediction for Online Identity Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the digital world, service providers lack the ability to accurately verify the identity of users interacting online, leading to potential fraudulent activities and impersonation, as existing security measures like security questions and two-factor authentication are insufficient.
Innovation Solution
A system that utilizes machine learning models to analyze event data from user interactions with graphical user interfaces, such as mouse movements, typing patterns, and device dynamics, to predict a user's age and identify potential fraudulent interactions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional security measures (security questions, two-factor authentication) are used for identity verification, then the implementation is simple and widely adopted, but they are insufficient to prevent fraudulent activities and impersonation
Solution Approach 1:
The patent introduces an intermediary evaluation service that acts as a mediator between the user and the service provider. This service collects behavioral biometric data from multiple sources, processes it through machine learning models, and provides fraud risk evaluations. The intermediary handles the complexity of behavioral analysis while keeping the user interface simple, thus improving reliability without significantly increasing perceived complexity for end users.
Solution Approach 2:
The patent replaces traditional mechanical security measures (security questions, SMS codes) with a behavioral biometric analysis system. Instead of relying on users to remember answers or access secondary devices, the system automatically analyzes typing patterns, mouse movements, and device interaction behaviors to verify identity. This substitution improves verification accuracy while maintaining ease of use.
2Measurement precision
If behavioral biometric data is collected from multiple input devices to improve fraud detection, then the detection accuracy improves, but the amount of data to be processed and the system complexity increase
Solution Approach 1:
The patent segments the fraud detection system into distinct functional modules: data collection from multiple input devices, behavioral biometric extraction, machine learning model processing, and fraud risk evaluation. Each module handles specific tasks independently, making the overall complex system manageable and maintainable while achieving high detection accuracy through coordinated operation of specialized components.
Solution Approach 2:
The system implements self-service by automatically collecting behavioral biometric data from multiple input devices without requiring user intervention. The machine learning models automatically process the collected data and generate fraud risk evaluations, eliminating the need for manual data processing and reducing operational complexity despite handling multiple data sources.
3Reliability
If machine learning models are used to analyze user behavior patterns, then the ability to detect fraudulent interactions improves, but the computational resources and processing time required increase
Solution Approach 1:
The patent applies preliminary action by pre-training machine learning models offline with extensive behavioral biometric data. The models are prepared in advance to recognize fraud patterns, so during actual user interactions, the computation required is minimized to inference rather than full training. This approach enables high detection reliability while reducing real-time computational resource consumption.
Solution Approach 2:
The system uses partial action by selectively applying machine learning analysis to specific behavioral indicators that are most indicative of fraud. Rather than analyzing all possible user actions equally, the model focuses on key behavioral biometrics such as typing rhythm and mouse movement patterns, reducing computational overhead while maintaining high detection accuracy.
Data Source
AI summary
The present technology includes receiving event data of a user from a user device while the user interacts with a graphical user interface (GUI) to access a service, where the event data includes behavioral biometrics of the user obtained from one or more input devices of the user device, and predicting, based on the event data, a projected age of the user, where predicting the age of the user includes inputting the event data into a machine learning model, where the machine learning model is configured to receive event data and output an age prediction for a user associated with the event data.