Dynamic Transaction Verification Using Geographic Behavior Models

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems face inefficiencies in integrating and verifying electronic exchanges of information due to incompatible data formats, leading to excessive computing and network resource consumption, and high error rates in fraud detection using static polygon spaces.

Innovation Solution

A system utilizing a machine learning model trained on geographic and transaction data to dynamically verify electronic exchanges, reducing resource consumption and improving fraud detection by predicting validity based on user behavior patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If static polygon spaces are used for fraud detection, then the verification process is simple to implement, but the error rate in fraud detection is high

Engineering Contradiction:

Improveease of implementationVSAvoidfraud detection accuracy

Core Design Contradiction:

Ease of manufactureVSReliability

Solution Approach 1:

The patent replaces static polygon spaces with dynamic verification that adapts to user behavior patterns. The system continuously learns from transaction data and adjusts verification parameters in real-time, transforming the rigid static approach into a flexible dynamic system that improves fraud detection accuracy while maintaining operational simplicity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The invention changes the parameters used for verification from fixed geographic polygon boundaries to dynamic parameters based on machine learning models. These models analyze user behavior patterns, device characteristics, and transaction contexts to dynamically adjust verification thresholds, thereby reducing error rates while keeping the system easy to implement.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If traditional verification systems are used, then the system structure is simple, but computing and network resource consumption is excessive

Engineering Contradiction:

Improvesystem structureVSAvoidcomputing and network resource consumption

Core Design Contradiction:

Device complexityVSUse of energy by moving object

Solution Approach 1:

The patent implements preliminary action by pre-training machine learning models offline using historical transaction data. This allows the system to perform complex analysis beforehand, so that during actual verification, only lightweight model inference is needed, significantly reducing real-time computing and network resource consumption while maintaining a relatively simple system structure.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention substitutes traditional mechanical verification methods (such as manual review and rule-based systems) with machine learning-based automated verification. This substitution reduces excessive resource consumption by enabling more efficient pattern recognition and decision-making, while the modular architecture keeps the overall system structure manageable.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If static verification methods are used, then the implementation is straightforward, but the system cannot adapt to user behavior patterns

Engineering Contradiction:

Improveease of operationVSAvoidadaptability to user behavior

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements self-service by enabling the verification system to automatically learn and adapt to user behavior patterns without requiring manual reconfiguration. The machine learning models continuously train on new data and autonomously adjust verification strategies, maintaining ease of operation while dramatically improving adaptability to changing user behaviors and fraud patterns.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The invention incorporates feedback loops where verification outcomes and new transaction data continuously feed back into the machine learning models. This feedback mechanism allows the system to adapt to user behavior patterns over time while maintaining straightforward operation, as the adaptation happens automatically through the feedback-driven learning process rather than manual intervention.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12513156B2Dynamic verification of an electronic exchange of information

Publication Date: 2025.12.30 CAPITAL ONE SERVICES LLC

AI summary

In some implementations, a verification device may receive a request for an electronic exchange of information. The verification device may receive geographic location information associated with the request for the electronic exchange of information. The verification device may determine, using a machine learning model and based on the geographic location information, a validity of the request for the electronic exchange of information. The verification device may determine whether to execute the electronic exchange of information based on the determination of the validity of the request for the electronic exchange of information. The verification device may perform one of executing the electronic exchange of information or rejecting the request for the electronic exchange of information based on the determination of whether to execute the electronic exchange of information.