Preemptive User Interaction Alerts via ML Exposure Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional authentication systems fail to prevent unauthorized interactions by not providing exposure-related information, leaving them ineffective in minimizing unauthorized interactions.

Innovation Solution

A system that continuously tracks and monitors user activity, identifies triggers for interactions, communicates with back-end systems to extract information using machine learning models, generates exposure characteristics, and transmits preemptive alerts to user devices to mitigate potential risks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If conventional authentication systems are used, then authentication process is simplified, but unauthorized interactions are not completely prevented

Engineering Contradiction:

Improveauthentication processVSAvoidprevention of unauthorized interactions

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system performs preliminary actions by continuously tracking user activity, identifying potential interactions, and generating exposure characteristics before the actual interaction occurs. This allows the system to send preemptive alerts to users, enabling them to take preventive measures before unauthorized interactions can compromise their security.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system establishes a feedback loop by continuously monitoring user activity, analyzing interaction risks using machine learning models, and providing real-time alerts to users. This feedback mechanism enables users to adjust their behavior based on risk assessments, thereby preventing unauthorized interactions while maintaining ease of operation.

Inventive Principle:

Principle #23Feedback

2Loss of information

If exposure related information is provided to users, then user awareness of risks is improved, but system complexity increases

Engineering Contradiction:

Improveexposure information provided to userVSAvoidsystem complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system introduces an intermediary layer consisting of machine learning models that automatically analyze user activity patterns and generate exposure characteristics. This intermediary processes complex data and translates it into actionable risk assessments, reducing the apparent complexity for users while providing comprehensive exposure information.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The machine learning models perform self-service by automatically tracking user activity, identifying potential interactions, and generating risk assessments without requiring user intervention. This automation handles the complexity internally while presenting simplified risk information to users, balancing information provision with system complexity.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If machine learning models are used to generate exposure characteristics, then accuracy of risk assessment is improved, but processing time increases

Engineering Contradiction:

Improverisk assessment accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system implements continuous tracking of user activity and continuous operation of machine learning models to generate exposure characteristics in real-time. This continuous processing ensures that risk assessments are always up-to-date and accurate without requiring batch processing delays, thereby maintaining measurement precision while minimizing time loss through ongoing analysis.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS10992765B2Machine learning based third party entity modeling for preemptive user interactions for predictive exposure alerting

Publication Date: 2021.04.27 BANK OF AMERICA CORP

AI summary

An electronic communication security system is typically configured for continuously tracking and monitoring user activity associated with a user, identifying a trigger based on continuously tracking and monitoring the user activity, wherein identifying the trigger is based on identifying that the user activity meets one or more conditions, determining initiation of an interaction between the user and a resource entity based on identifying the trigger, communicating with back-end systems to extract information associated with the resource entity associated with the interaction, wherein the information comprises an output that is generated by one or more machine learning models, generating exposure characteristics for the interaction based on the output associated with the resource entity and user data associated with the user, wherein the exposure characteristics are unique to the interaction and the user, and in response to generating the exposure characteristics, transmitting the exposure characteristics to a user device.