Device Fingerprinting Rules for Fraudulent Transaction Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fraudsters use the same computing devices to emulate legitimate users for fraudulent transactions, posing a challenge in identifying and preventing such activities in online networks.
Innovation Solution
A device analytics engine that utilizes pre-programmed rules to analyze device data, including parameters like SDK type, user cookies, and IP addresses, to identify device identifiers and generate scores for determining whether a transaction is legitimate or fraudulent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional user identification methods are used, then legitimate users can access services, but fraudsters can easily create fake identities and commit fraud
Solution Approach 1:
The patent segments device identification into multiple distinct parameters including device hardware identifiers, software environment characteristics, network connection details, and behavioral patterns. Each parameter is analyzed separately and then combined to form a comprehensive device fingerprint, enabling more accurate fraud detection without requiring a single complex identification system
Solution Approach 2:
The system changes from traditional single-parameter user identification to multi-parameter device fingerprinting. By collecting and analyzing multiple device parameters (hardware specs, software versions, network information, behavioral metrics), the system transforms the identification approach to achieve higher reliability in distinguishing legitimate users from fraudsters
2Measurement precision
If multiple device parameters are analyzed to identify fraudulent devices, then fraud detection accuracy improves, but data processing complexity and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-collecting and storing device parameters during normal operations before fraud detection is needed. Device fingerprints are built incrementally as users interact with the system, so when fraud detection is required, the analysis can proceed more efficiently using pre-prepared data rather than collecting everything from scratch
Solution Approach 2:
The patent introduces device fingerprints as intermediary representations that summarize multiple raw device parameters into consolidated profiles. These fingerprints serve as intermediaries between the complex multi-parameter data and the fraud detection algorithms, simplifying the processing while maintaining identification accuracy
3Productivity
If device fingerprints are created and stored for analysis, then fraudulent transactions can be detected, but user privacy concerns and data storage requirements increase
Solution Approach 1:
The system extracts only the necessary device characteristics needed for fraud detection while leaving out personally identifiable information. By taking out only the relevant technical parameters (hardware identifiers, software versions, network details) and excluding sensitive user data, the system achieves fraud detection efficiency while minimizing privacy intrusion
Data Source
AI summary
Systems, methods, and computer program products for identifying a fraudulent device. A device analytics engine receives device data from a computing device, the device data including parameters associated with the computing device. The device analytics engine selects a set of rules in a plurality of rules that indicate at least one parameter in the plurality of parameters in the device data for determining a device identifier. The set of rules are evaluated in order until the device identifier is determined from the at least one parameter indicated in the set of rules, the device data, and previously stored data from multiple computing devices. A score is generated for the computing device using one or more of the device identifier, device data, a set of rules, and previously receive device data that corresponds to the device identifier. A computing device is identified as a fraudulent computing device based on the score.