Automated Fraud Detection Using Device Fingerprinting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current payment transaction anti-fraud systems are inefficient due to the time-consuming and error-prone manual review process, especially since 20% of online commerce transactions require manual verification, which accounts for over 50% of overall anti-fraud costs, and there are challenges in auditing Bitcoin and cryptocurrency transactions for compliance with anti-money laundering and fraud detection.

Innovation Solution

The system uses electronic signatures based on attributes like browser fingerprints, computer fingerprints, IP addresses, and typing patterns to uniquely identify users across merchants and payment networks, allowing for automated transaction authentication and fraud detection by comparing hashes of attributes stored at a central location, reducing the need for manual reviews and enhancing compliance with anti-money laundering regulations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If automated fraud detection systems are implemented, then transaction processing speed is improved, but detection accuracy deteriorates due to the complexity of identifying fraudulent patterns

Engineering Contradiction:

Improvetransaction processing speedVSAvoidfraud detection accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The fraud detection system segments the transaction evaluation into multiple independent scoring components (device fingerprinting, behavioral analysis, location verification, payment instrument validation). Each component generates an independent score that is aggregated to produce an overall fraud risk assessment, enabling parallel processing while maintaining comprehensive detection accuracy

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary scoring mechanism that translates complex fraudulent pattern recognition into quantifiable risk scores. This intermediary layer processes multiple data sources and transforms them into a unified evaluation framework that can be efficiently computed while preserving detection precision

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If manual review processes are used for transaction verification, then fraud detection accuracy is improved, but processing time increases and operational costs rise

Engineering Contradiction:

Improvefraud detection accuracyVSAvoidmanual review time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary automated evaluation of transactions using multiple verification mechanisms (device fingerprinting, behavioral biometrics, location analysis) before manual review. This preliminary action pre-screens transactions to identify only those requiring human attention, reducing manual review time while maintaining high detection accuracy through layered verification

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system enables self-service verification through automated device fingerprinting and behavioral analysis that independently assess transaction risk without human intervention. These self-executing verification processes handle routine fraud detection, freeing manual reviewers to focus only on complex cases

Inventive Principle:

Principle #25Self-service

3Reliability

If comprehensive transaction monitoring is implemented to detect fraud patterns, then fraud detection capability is improved, but system complexity and computational resources increase

Engineering Contradiction:

Improvefraud detection capabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The monitoring system divides comprehensive fraud detection into segmented analysis modules (device fingerprinting, behavioral biometrics, geolocation tracking, payment instrument validation). Each module independently processes specific data types and generates focused risk scores, reducing overall system complexity while maintaining comprehensive detection capability through modular architecture

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system employs universal scoring mechanisms that can evaluate multiple different fraud indicators through a common framework. The same scoring infrastructure handles device fingerprints, behavioral patterns, location data, and payment instrument validation, reducing computational overhead while maintaining comprehensive monitoring capability

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10037533B2Systems and methods for detecting relations between unknown merchants and merchants with a known connection to fraud

Publication Date: 2018.07.31 ACUANT

AI summary

An example merchant fraud system may include an automated system for collecting contextual relationship information, plus a routine for analyzing additional data related to sanctions. The system may also include an automated analysis summary routine for creating condensed information subsets or graphlets containing information about sanction entities, some of which can be entities themselves, organized in a data retrieval system, such that an automated relationship examination system can check data from transactions and automatically identify and flag potentially suspect relationship aspects. The system may issue a fraud warning and may review a flagged transaction cluster, accepting transactions when transaction cluster items do not contain links to a known bad entity. Based on a hit with a suspect entity, the breadth of the examined co-related items may be expanded, and if that expansion results in one or more suspect connections, a transaction is rejected and sent for further review.